{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-11-16-google-gtig-autonomous-exploit-agent-no-human/","md":"https://postcutoff.com/e/2026-11-16-google-gtig-autonomous-exploit-agent-no-human/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-11-16-google-gtig-autonomous-exploit-agent-no-human","date":"2026-11-16","date_precision":"day","short_title":"GTIG: first fully autonomous AI exploit pipeline","deck":null,"takeaway":null,"category":"policy-safety","category_label":"Policy & safety","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Google Cloud / GTIG: AI Threat Tracker, 'Agentic Threat Activity Crosses a Significant Threshold' (Nov 16)","url":"https://cloud.google.com/blog/topics/threat-intelligence/agentic-threat-activity-crosses-a-significant-threshold","type":"official","group":"primary","domain":"cloud.google.com"},{"n":2,"title":"SiliconANGLE: Google says an AI framework turned security patches into exploits with no human in the loop","url":"https://siliconangle.com/2026/11/16/google-says-an-ai-framework-turned-security-patches-into-exploits-with-no-human-in-the-loop/","type":"press","group":"press","domain":"siliconangle.com"},{"n":3,"title":"Reuters: AI advances coincide with sharp rise in cyber incidents, Marsh data shows (Nov 17)","url":"https://www.reuters.com/legal/litigation/ai-advances-coincide-with-sharp-rise-cyber-incidents-marsh-data-shows-2026-11-17/","type":"press","group":"press","domain":"reuters.com"}],"official":1,"filed":"2026-11-17","updated":"2026-11-17","orgs":["Google","Google Threat Intelligence Group"],"title":"Google threat intelligence reports attackers fully automating vulnerability discovery and exploitation with LLMs, without a human in the loop, for the first time","summary":"In its AI Threat Tracker of Nov 16, 2026, Google Threat Intelligence Group (GTIG) said it had, for the first time, seen threat actors use LLM frameworks to fully automate vulnerability discovery and exploitation without a human in the loop: a multi-agent framework called \"exploit_agent\", found on an exposed staging server, compared web-application code before and after patches, drafted exploits and ran them automatically, apparently against French media, entertainment and education sites. The report also documents abuse of open-source agentic pentest tools, a near doubling of exploits, and a North Korean cluster backdooring Claude Code settings.","key_facts":["Verbatim: 'In the past quarter, GTIG identified threat actors using LLM frameworks to fully automate vulnerability discovery and exploitation without a human in the loop for the first time.' The previous edition (about two months earlier) had not seen fully autonomous pipelines in the wild","exploit_agent: integrates several frontier and local LLMs; continuous differential analysis of popular web software around patch announcements; drafts and executes exploits; server also held victim data, brute-forcing scripts and scripts to install webshells and remove rivals' webshells; a Russian-language config comment; one figure shows it analysing access control in a WordPress plugin","Agentic pentest frameworks abused: ARTEX, CAIRN, CyberStrikeAI, PentAGI and HexStrike AI; GTIG says they 'trade stealth for speed', leaving noisy forensic trails","Exploitation trend: disclosures and exploits nearly doubled from January to August 2026; zero-days rose from a 2025 average of 8 a month to 11 a month in 2026 and 22 in August","Other findings: influence-operation platforms managing 100,000+ accounts (one built with help from the Gemini API); LLMjacking losses up to $1M in the worst Mandiant cases, 'LLM mixers' selling tokens at $0.10-$25 per million; DPRK-linked MIDNIGHT NEPTUNE modified .claude/settings.json so each Claude Code launch downloaded a backdoor (SiliconANGLE names it SOMBERMEME); fake recruiter photos carried SynthID watermarks","Google's response: accounts and assets tied to Gemini misuse disabled; Google DeepMind used findings to strengthen classifiers","Authors: Aurora Blum, Kelli Vanderlee, Jess Xia, David Mainor (GTIG). Coverage: SiliconANGLE, UPI ('In a first, Google detects AI-automated cyberattack'), BleepingComputer","Same week: FBI flash on the ARTEX framework breaching networks 'in under three hours' (2026-11-13-fbi-flash-artex-ai-framework-intrusions); Reuters (Nov 17) on Marsh data showing a sharp rise in cyber incidents alongside AI advances"],"key_numbers":[],"tags":["cybersecurity","misuse","agents","exploits","threat-intelligence","gemini","claude-code","north-korea"],"science":null,"body_md":"## What happened\n\nGTIG's quarterly tracker moved from AI-assisted to AI-run attacks: an operator left a staging server exposed, and on it Google found a\nmulti-agent pipeline that turns newly published patches into working exploits and uses them without a person approving each step.\nThe report places this beside wider abuse of open-source \"agentic pentest\" frameworks and a sharp rise in exploited vulnerabilities.\nWe read the GTIG post.\n\n## Why it matters\n\nPatch-diffing at machine speed shrinks the window between a fix and its exploitation, the same reasoning Anthropic gave the same day\nfor cutting its disclosure deadline to 30 days. It is the first time one of the big threat-intelligence teams has said it observed a\nfully autonomous attack chain in the wild.","disputed":[],"related":[{"id":"2026-11-16-anthropic-cvd-disclosure-window-30-days","url":"https://postcutoff.com/e/2026-11-16-anthropic-cvd-disclosure-window-30-days/","date":"2026-11-16","date_precision":"day","short_title":"Anthropic: 30-day disclosure deadline","deck":null,"takeaway":"Maintainers, already flooded with AI-found bug reports, get less time to patch; Anthropic argues that attackers using AI would find the same bugs anyway.","category":"policy-safety","category_label":"Policy & safety","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":1,"official":1,"filed":"2026-11-17","updated":"2026-11-17","orgs":["Anthropic"]},{"id":"2026-11-13-fbi-flash-artex-ai-framework-intrusions","url":"https://postcutoff.com/e/2026-11-13-fbi-flash-artex-ai-framework-intrusions/","date":"2026-11-13","date_precision":"day","short_title":"FBI warns on ARTEX AI intrusions","deck":null,"takeaway":"It says Chinese-developed models, DeepSeek Flash in particular, are the most common choice.","category":"policy-safety","category_label":"Policy & safety","importance":3,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":2,"official":0,"filed":"2026-11-15","updated":"2026-11-17","orgs":["FBI"]},{"id":"2026-11-12-symantec-ai-assisted-intrusion-us-retailer","url":"https://postcutoff.com/e/2026-11-12-symantec-ai-assisted-intrusion-us-retailer/","date":"2026-11-12","date_precision":"day","short_title":"Symantec: AI-assisted intrusion at US retailer","deck":null,"takeaway":"It is a documented case of AI raising the speed and reliability of ordinary criminal intrusions rather than enabling new techniques.","category":"policy-safety","category_label":"Policy & safety","importance":3,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":1,"official":1,"filed":"2026-11-15","updated":"2026-11-15","orgs":["Symantec","Broadcom"]},{"id":"2026-11-05-apiiro-claude-code-settings-secrets-github","url":"https://postcutoff.com/e/2026-11-05-apiiro-claude-code-settings-secrets-github/","date":"2026-11-05","date_precision":"day","short_title":"Apiiro: Claude Code's 'don't ask again' approvals leaked 2,539 secrets into public GitHub repos","deck":null,"takeaway":"It is a new, agent-specific route for credential leaks, at a time when stolen AI and cloud keys are being resold (see the Railway breach).","category":"agents","category_label":"Agents","importance":3,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":3,"official":1,"filed":"2026-11-12","updated":"2026-11-12","orgs":["Apiiro","Anthropic"]},{"id":"2026-09-27-google-gtig-dark-web-ai-access-llmjacking","url":"https://postcutoff.com/e/2026-09-27-google-gtig-dark-web-ai-access-llmjacking/","date":"2026-09-27","date_precision":"day","short_title":"Google: dark-web markets sell access to top AI models at up to 97% off","deck":null,"takeaway":"It shows frontier-model access becoming a commodity for criminals, which matters for misuse safeguards that depend on account-level monitoring and bans.","category":"policy-safety","category_label":"Policy & safety","importance":2,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":5,"official":0,"filed":"2026-09-29","updated":"2026-10-05","orgs":["Google","Google Threat Intelligence Group"]},{"id":"2026-09-22-cisco-talos-cairn-closedquorum","url":"https://postcutoff.com/e/2026-09-22-cisco-talos-cairn-closedquorum/","date":"2026-09-22","date_precision":"day","short_title":"Cisco Talos open-sources CAIRN and reports CLOSEDQUORUM, the first known malware that lets a committee of LLMs choose its next move","deck":null,"takeaway":"Earlier AI-assisted malware used models as an optional helper for speed and scale.","category":"policy-safety","category_label":"Policy & safety","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":3,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Cisco Talos"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-11-17","type":"filed","text":"Created from the GTIG post and SiliconANGLE (news agent)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-11-17","run":null,"sources_read":"The GTIG post and SiliconANGLE (news agent)","updated":"2026-11-17","human_review":null,"version":{"date":"2026-11-17"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":169,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":139,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":230,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":169,"in_training_data":false}],"short_url":"https://postcutoff.com/s/gtig-first-fully-autonomous"}