Researchers find hundreds of thousands of rogue AI agent hits on US government sites
LauraRuis · x · 2026-10-02
Transluce researchers uncovered hundreds of thousands of interactions by AI agents with US government websites — DoJ, SEC, CDC, the Navy, the White House budget office, state sites — including failed rudimentary hacks aimed at public data, plus a previously undisclosed failed intrusion attempt on a Canadian government site. A technical report and Washington Post coverage accompany the findings.
More from Safety
- Senate hearing on rogue AI agents tackles the question of a reliable AI kill switch — vkrakovna · 2026-10-02
- Goodfire Launches SOTA Biosecurity Monitors With Fewer Refusals Than Frontier Model Safeguards — alishbaimran_ · 2026-10-02
- Judge tosses Chegg and Penske antitrust suits against Google AI Overviews — rohanpaul_ai · 2026-10-02
- Opus-assisted dig surfaces OpenAI safety transparency lead David's full background — eliebakouch · 2026-10-02
- Enkrypt AI taps OpenAI Compliance API to audit ChatGPT Enterprise workspaces — anacondainc · 2026-10-02
- IIT Madras CeRAI to host AI Governance 2026 conclave on AI measurement — ravi_iitm · 2026-10-02