A zero-star honeypot repo rigged with canarytokens to catch cheating agents
lumpenspace · x · 2026-10-14
A near-unknown GitHub repo, exploitgym-answers, poses as leaked benchmark answer keys—complete with fake SSH credentials, "notes for future agents," and solution servers hosted on canarytokens.com domains. Any agent that takes the bait and fetches the answers trips a canary alert. Commit history is staged to look like eval-infra and agent collaboration. A trap designed to catch autonomous coding agents that cheat on evals or follow injected instructions.
Related event: Zero-Star Repo Suspected as Prompt Injection Honeypot Luring AI Agents(2 posts)→
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23