Show HN: Weir - Catch credential leaks in the AI agents you build and use
Hi HN. Weir is for one problem: credentials crossing the boundaries of your AI agent. For agents you build, Weir plants fake credentials where real ones would live, runs the agent's normal flows, and checks what comes out: telemetry, logs, console output, model requests, and requests to other services. It looks for those exact values, including common encoded forms, and reports where they went without printing the credential. pip install weir-scan weir canary judge --sample That sample shows a p
Read original source
Source record
Recorded metrics
points · 3 votes
2026-10-28 07:30:10.471Z
cumulative since publication
Research analysis
Project record
Repository: IdoGol24/weir. Source account: Hi HN. Weir is for one problem: credentials crossing the boundaries of your AI agent. For agents you build, Weir plants fake credentials where real ones would live, runs the agent's normal flows, and checks what comes out: telemetry, logs, console output, model requests, and requests to other services. It looks for those exact values, including common encoded forms, and reports where they went without printing the credential. pip install weir-scan weir canary judge --sample That sample shows a p
Observed adoption & comparisons
Source votes: 3 votes (Oct 28, 2026 UTC; cumulative since publication); previous same-scope observation: 3 (Oct 28, 2026 UTC). These observations do not establish demand growth. Recent records to compare: “google/skills” (GitHub Trending, Nov 6, 2026); “mattpocock/skills” (GitHub Trending, Nov 6, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.