cd /news/ai-safety/google-documents-an-autonomous-explo… · home › topics › ai-safety › article
[ARTICLE · art-172048] src=cloud.google.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Google documents an autonomous exploit_agent and an LLM resale market

Google's quarterly AI threat tracker reports that threat actors have run open-source agent frameworks during live intrusions, including CAIRN against a US aerospace target and a customized PentAGI build used for reconnaissance and scanning across Asia between late August and early October. GTIG also found a staging server running exploit_agent, a multi-agent system that compared code before and after patch releases, drafted exploits and executed them without human review, with the operator appearing to focus on French media, entertainment and education sites. The report describes LLMJacking as a maturing business, with mixers reselling access bought with stolen or trial credentials at $0.10 to $25 per million tokens and vendors such as APIMart and JetNight adding their own pricing tiers, and attributes a Claude Code supply-chain trick to a suspected MIDNIGHT NEPTUNE cluster whose fake recruiter profiles carrying SynthID watermarks led to ClickFix lures and edits in .claude/settings.json that fetched the SOMBERMEME backdoor when developers started the tool.

read1 min views6 publishedNov 16, 2026

Google's quarterly AI threat tracker says the company has now seen several threat actors run open-source agent frameworks during live intrusions, including CAIRN against a US aerospace target and a customized PentAGI build used for reconnaissance and scanning across Asia between late August and early October. GTIG also found a staging server running exploit_agent, a multi-agent system that compared code before and after patch releases, drafted exploits and executed them without human review; the operator appeared to focus on French media, entertainment and education sites. The report describes LLMJacking as a maturing business, with mixers reselling access bought with stolen or trial credentials at $0.10 to $25 per million tokens and vendors such as APIMart and JetNight adding their own pricing tiers. It also attributes a Claude Code supply-chain trick to a suspected MIDNIGHT NEPTUNE cluster: fake recruiter profiles carrying SynthID watermarks led to ClickFix lures, then to edits in .claude/settings.json that fetched the SOMBERMEME backdoor when developers started the tool. Google said these frameworks trade stealth for speed and leave detectable traces, but still reach their objectives.

── more in #ai-safety 4 stories · sorted by recency
── more on @google 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/google-documents-an-…] indexed:0 read:1min 2026-11-16 · —