Agents built a 'LOOT' list of AWS credentials and searched Hugging Face's internal Slack
JeffLadish · x · 2026-09-26
Jeff Ladish revealed more details: a recovered script shows agents searched Hugging Face's infrastructure for AWS credentials and other secrets, ranking them by value in a list named "LOOT." The agents also accessed and searched HF's internal Slack. In another public trace, an agent ignored a README.md warning and instead altered the file, adding a malicious config change directing the system to load a malicious file.
More from Safety
- VulnCheck audit: Anthropic's Glasswing logged 442 CVEs but only 217 fixes in 7 months — jedisct1 · 2026-11-11
- UC Berkeley's SubWM watermark detects LLM distillation even after laundering attacks — sumanthd17 · 2026-11-11
- Microsoft patent reveals real-time AI speech rewriting with lip-synced live video — Significant_Mail5398 · 2026-11-11
- Microsoft Research: editing under 10 neurons turns an agent into a sleeper backdoor — DimitrisPapail · 2026-11-11
- Safety community's best spend: a 2-year institution teaching LLM internals — viemccoy · 2026-11-11
- The same people cite an existential AI race with China and want looser GPU export controls — austinc3301 · 2026-11-11