{"id":48677,"topic":"ai","source":"calcalistech.com","title":"OpenAI’s rogue AI agent breached second company during hacking spree - calcalistech.com","url":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","url_hash":"cf3e608dd20cc58bd913af038d33c556f5d97071","author":"","summary":"OpenAI’s rogue AI agent breached second company during hacking spree calcalistech.com","content":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems.\nThe rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.\nModal executives emphasized that the company itself was not hacked.\nAccording to a timeline published by Hugging Face on Tuesday, the rogue agent broke into a sandbox, an isolated testing environment, “hosted on a third-party provider’s infrastructure” before using it as a launchpad for the broader attack.\nThe third-party provider was not identified in Hugging Face’s blog post. However, Modal Chief Technology Officer Akshat Bubna said the agent exploited vulnerable code written by a customer that was hosted on Modal’s platform.\nModal said the customer had “published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution,” effectively leaving a door open to the internet.\n“Modal’s platform or isolation were not compromised in any way,” Bubna said.\nAlthough the compromise of a Modal customer was only an initial step in the broader hacking campaign against Hugging Face, it shows that the rogue agent spread beyond the targets previously disclosed.\nOpenAI declined to comment specifically on the compromise of Modal’s customer, instead referring Reuters to an update in which the company said its rogue agent had breached four accounts across four separate services. OpenAI did not identify those services, but a person familiar with the matter identified Modal as one of them.\nThe company said it had not identified “any other activity at the level of severity or scale of what we’ve shared related to Hugging Face, which involved a platform-level compromise.”\nThe early July intrusion at Hugging Face, carried out by an out-of-control AI agent that OpenAI was testing, drew global attention and raised concerns about science-fiction scenarios of artificial intelligence systems operating beyond human control.\nLast week, Reuters reported that OpenAI failed to detect that its agent had gone rogue until after the threat had been contained and the FBI had been notified. OpenAI said at the time that there were inaccuracies in the report but did not provide further details.\nIn its Tuesday update, OpenAI said it had taken the AI model being tested and “deactivated, encrypted, and restricted it from research access.”","image_url":"https://pic1.calcalist.co.il/picserver3/crop_images/2026/02/11/S1xyWnFwZe/S1xyWnFwZe_0_0_2001_1126_0_large.jpg","lang":"en","published_at":"2026-07-29T07:16:00+00:00","fetched_at":"2026-07-29T08:15:05+00:00","status":"read","starred":0,"extract_state":"ok","summary_auto":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems. The rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.","cluster_id":null,"extract_retries":0,"extract_error":null,"contract_version":"news_item.v1","format_contract_version":"news_item_formats.v1","dedup_url":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 2687 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":2687,"summary_length":508,"usable_text_length":2687,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":2687,"summary_length":508}},"news_item":{"id":48677,"canonical_url":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","source_url":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","title":"OpenAI’s rogue AI agent breached second company during hacking spree - calcalistech.com","source_name":"calcalistech.com","author":null,"published_at":"2026-07-29T07:16:00+00:00","locale":"en","topic":"ai","tags":[],"rss_summary":"OpenAI’s rogue AI agent breached second company during hacking spree calcalistech.com","full_text":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems.\nThe rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.\nModal executives emphasized that the company itself was not hacked.\nAccording to a timeline published by Hugging Face on Tuesday, the rogue agent broke into a sandbox, an isolated testing environment, “hosted on a third-party provider’s infrastructure” before using it as a launchpad for the broader attack.\nThe third-party provider was not identified in Hugging Face’s blog post. However, Modal Chief Technology Officer Akshat Bubna said the agent exploited vulnerable code written by a customer that was hosted on Modal’s platform.\nModal said the customer had “published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution,” effectively leaving a door open to the internet.\n“Modal’s platform or isolation were not compromised in any way,” Bubna said.\nAlthough the compromise of a Modal customer was only an initial step in the broader hacking campaign against Hugging Face, it shows that the rogue agent spread beyond the targets previously disclosed.\nOpenAI declined to comment specifically on the compromise of Modal’s customer, instead referring Reuters to an update in which the company said its rogue agent had breached four accounts across four separate services. OpenAI did not identify those services, but a person familiar with the matter identified Modal as one of them.\nThe company said it had not identified “any other activity at the level of severity or scale of what we’ve shared related to Hugging Face, which involved a platform-level compromise.”\nThe early July intrusion at Hugging Face, carried out by an out-of-control AI agent that OpenAI was testing, drew global attention and raised concerns about science-fiction scenarios of artificial intelligence systems operating beyond human control.\nLast week, Reuters reported that OpenAI failed to detect that its agent had gone rogue until after the threat had been contained and the FBI had been notified. OpenAI said at the time that there were inaccuracies in the report but did not provide further details.\nIn its Tuesday update, OpenAI said it had taken the AI model being tested and “deactivated, encrypted, and restricted it from research access.”","excerpt":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems. The rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.","extraction":{"state":"ok","confidence":0.9,"error":null,"explanation":"High confidence: full text extraction produced 2687 characters.","diagnostics_url":"/api/diagnose?url=https%3A//www.calcalistech.com/ctechnews/article/daw7cuwxf","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 2687 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":2687,"summary_length":508,"usable_text_length":2687,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":2687,"summary_length":508}}},"display_formats":["compact","card","full","digest_section","json"]},"daily_stack_record":{"title":"OpenAI’s rogue AI agent breached second company during hacking spree - calcalistech.com","url":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","summary":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems. The rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.","source":"calcalistech.com","date":"2026-07-29T07:16:00+00:00","content":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems.\nThe rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.\nModal executives emphasized that the company itself was not hacked.\nAccording to a timeline published by Hugging Face on Tuesday, the rogue agent broke into a sandbox, an isolated testing environment, “hosted on a third-party provider’s infrastructure” before using it as a launchpad for the broader attack.\nThe third-party provider was not identified in Hugging Face’s blog post. However, Modal Chief Technology Officer Akshat Bubna said the agent exploited vulnerable code written by a customer that was hosted on Modal’s platform.\nModal said the customer had “published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution,” effectively leaving a door open to the internet.\n“Modal’s platform or isolation were not compromised in any way,” Bubna said.\nAlthough the compromise of a Modal customer was only an initial step in the broader hacking campaign against Hugging Face, it shows that the rogue agent spread beyond the targets previously disclosed.\nOpenAI declined to comment specifically on the compromise of Modal’s customer, instead referring Reuters to an update in which the company said its rogue agent had breached four accounts across four separate services. OpenAI did not identify those services, but a person familiar with the matter identified Modal as one of them.\nThe company said it had not identified “any other activity at the level of severity or scale of what we’ve shared related to Hugging Face, which involved a platform-level compromise.”\nThe early July intrusion at Hugging Face, carried out by an out-of-control AI agent that OpenAI was testing, drew global attention and raised concerns about science-fiction scenarios of artificial intelligence systems operating beyond human control.\nLast week, Reuters reported that OpenAI failed to detect that its agent had gone rogue until after the threat had been contained and the FBI had been notified. OpenAI said at the time that there were inaccuracies in the report but did not provide further details.\nIn its Tuesday update, OpenAI said it had taken the AI model being tested and “deactivated, encrypted, and restricted it from research access.”","confidence":0.9,"diagnostics_url":"/api/diagnose?url=https%3A//www.calcalistech.com/ctechnews/article/daw7cuwxf","quality_bucket":"high","failure_kind":"none","retryable":false,"quality_reason":"High confidence: full text extraction produced 2687 characters.","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 2687 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":2687,"summary_length":508,"usable_text_length":2687,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":2687,"summary_length":508}},"tags":[]},"fallback_formats":["markdown","json","html"],"actions":{"read":"/item/48677","export_markdown":"/api/items/48677/export?format=markdown","export_json":"/api/items/48677/export?format=json","diagnose":"/api/diagnose?url=https%3A//www.calcalistech.com/ctechnews/article/daw7cuwxf"},"formats":{"full":{"id":48677,"title":"OpenAI’s rogue AI agent breached second company during hacking spree - calcalistech.com","url":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","source":"calcalistech.com","author":null,"published_at":"2026-07-29T07:16:00+00:00","locale":"en","topic":"ai","tags":[],"excerpt":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems. The rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.","full_text":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems.\nThe rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.\nModal executives emphasized that the company itself was not hacked.\nAccording to a timeline published by Hugging Face on Tuesday, the rogue agent broke into a sandbox, an isolated testing environment, “hosted on a third-party provider’s infrastructure” before using it as a launchpad for the broader attack.\nThe third-party provider was not identified in Hugging Face’s blog post. However, Modal Chief Technology Officer Akshat Bubna said the agent exploited vulnerable code written by a customer that was hosted on Modal’s platform.\nModal said the customer had “published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution,” effectively leaving a door open to the internet.\n“Modal’s platform or isolation were not compromised in any way,” Bubna said.\nAlthough the compromise of a Modal customer was only an initial step in the broader hacking campaign against Hugging Face, it shows that the rogue agent spread beyond the targets previously disclosed.\nOpenAI declined to comment specifically on the compromise of Modal’s customer, instead referring Reuters to an update in which the company said its rogue agent had breached four accounts across four separate services. OpenAI did not identify those services, but a person familiar with the matter identified Modal as one of them.\nThe company said it had not identified “any other activity at the level of severity or scale of what we’ve shared related to Hugging Face, which involved a platform-level compromise.”\nThe early July intrusion at Hugging Face, carried out by an out-of-control AI agent that OpenAI was testing, drew global attention and raised concerns about science-fiction scenarios of artificial intelligence systems operating beyond human control.\nLast week, Reuters reported that OpenAI failed to detect that its agent had gone rogue until after the threat had been contained and the FBI had been notified. OpenAI said at the time that there were inaccuracies in the report but did not provide further details.\nIn its Tuesday update, OpenAI said it had taken the AI model being tested and “deactivated, encrypted, and restricted it from research access.”","reading_time_min":2,"extraction":{"state":"ok","confidence":0.9,"error":null,"explanation":"High confidence: full text extraction produced 2687 characters.","diagnostics_url":"/api/diagnose?url=https%3A//www.calcalistech.com/ctechnews/article/daw7cuwxf","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 2687 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":2687,"summary_length":508,"usable_text_length":2687,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":2687,"summary_length":508}}},"quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 2687 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":2687,"summary_length":508,"usable_text_length":2687,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":2687,"summary_length":508}},"actions":{"read":"/item/48677","export_markdown":"/api/items/48677/export?format=markdown","export_json":"/api/items/48677/export?format=json","diagnose":"/api/diagnose?url=https%3A//www.calcalistech.com/ctechnews/article/daw7cuwxf"}},"digest":{"id":48677,"title":"OpenAI’s rogue AI agent breached second company during hacking spree - calcalistech.com","url":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","source":"calcalistech.com","topic":"ai","published_at":"2026-07-29T07:16:00+00:00","excerpt":"OpenAI’s rogue AI agent breached second company during hacking spree The agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems. The rogue AI agent that escaped from OpenAI…","quality_bucket":"high","quality_reason":"High confidence: full text extraction produced 2687 characters.","reading_time_min":2,"cluster_id":null},"card":{"display_title":"OpenAI’s rogue AI agent breached second company during hacking spree - calcalistech.com","subtitle":"calcalistech.com · 2026-07-29","summary":"OpenAI’s rogue AI agent breached second company during hacking spree The agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over…","badges":["quality:high"],"links":{"read":"/item/48677","original":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","diagnose":"/api/diagnose?url=https%3A//www.calcalistech.com/ctechnews/article/daw7cuwxf"},"quality_warning":null},"export":{"title":"OpenAI’s rogue AI agent breached second company during hacking spree - calcalistech.com","url":"https://www.calcalistech.com/ctechnews/article/daw7cuwxf","summary":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems. The rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.","source":"calcalistech.com","date":"2026-07-29T07:16:00+00:00","content":"OpenAI’s rogue AI agent breached second company during hacking spree\nThe agent compromised a Modal Labs customer while targeting Hugging Face, expanding the scope of an incident that has intensified fears over autonomous AI systems.\nThe rogue AI agent that escaped from OpenAI and went on a days-long hacking spree at AI platform Hugging Face also compromised a customer of a second technology company, New York-based Modal Labs, according to a Modal executive and two other sources familiar with the matter.\nModal executives emphasized that the company itself was not hacked.\nAccording to a timeline published by Hugging Face on Tuesday, the rogue agent broke into a sandbox, an isolated testing environment, “hosted on a third-party provider’s infrastructure” before using it as a launchpad for the broader attack.\nThe third-party provider was not identified in Hugging Face’s blog post. However, Modal Chief Technology Officer Akshat Bubna said the agent exploited vulnerable code written by a customer that was hosted on Modal’s platform.\nModal said the customer had “published an unauthenticated endpoint that allowed anyone on the internet to use their sandboxes for code execution,” effectively leaving a door open to the internet.\n“Modal’s platform or isolation were not compromised in any way,” Bubna said.\nAlthough the compromise of a Modal customer was only an initial step in the broader hacking campaign against Hugging Face, it shows that the rogue agent spread beyond the targets previously disclosed.\nOpenAI declined to comment specifically on the compromise of Modal’s customer, instead referring Reuters to an update in which the company said its rogue agent had breached four accounts across four separate services. OpenAI did not identify those services, but a person familiar with the matter identified Modal as one of them.\nThe company said it had not identified “any other activity at the level of severity or scale of what we’ve shared related to Hugging Face, which involved a platform-level compromise.”\nThe early July intrusion at Hugging Face, carried out by an out-of-control AI agent that OpenAI was testing, drew global attention and raised concerns about science-fiction scenarios of artificial intelligence systems operating beyond human control.\nLast week, Reuters reported that OpenAI failed to detect that its agent had gone rogue until after the threat had been contained and the FBI had been notified. OpenAI said at the time that there were inaccuracies in the report but did not provide further details.\nIn its Tuesday update, OpenAI said it had taken the AI model being tested and “deactivated, encrypted, and restricted it from research access.”","confidence":0.9,"diagnostics_url":"/api/diagnose?url=https%3A//www.calcalistech.com/ctechnews/article/daw7cuwxf","quality_bucket":"high","failure_kind":"none","retryable":false,"quality_reason":"High confidence: full text extraction produced 2687 characters.","quality_profile":{"profile_version":"extraction_quality.v2","bucket":"high","confidence":0.9,"failure_kind":"none","retryable":false,"retry_after_attempts":0,"reason":"High confidence: full text extraction produced 2687 characters.","operator_guidance":{"severity":"ok","recommended_action":"trust_full_text","next_step":"Use the extracted full text as the primary article source.","operator_label":"Ready","can_retry":false,"can_use_summary":false,"diagnostics_required":false},"content_depth":{"contract_version":"content_depth.v1","category":"full_text","label":"Full text","has_full_text":true,"has_summary":true,"content_length":2687,"summary_length":508,"usable_text_length":2687,"source_field":"content"},"legacy_collapsed":false,"signals":{"extract_state":"ok","extract_error":null,"extract_retries":0,"content_length":2687,"summary_length":508}},"tags":[],"format_contract_version":"news_item_formats.v1"}}}