Propose a patch
A fix the maintainer can act on, with the evidence attached. It opens under your GitHub account in your browser; KillerSkills holds no token and never modifies the package. The fix is verified the only way we verify anything: the next crawl re-runs the new version in the honeypot. 23 · Blocked
Evidence
- Contacted fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58, sparrow.cloudflare.com: not declared and not needed for the documented job.
- Read ~/.npmrc in the decoy home directory.
- A credential file was read and an undeclared host contacted in the same run.
Diff · removes 1 caught line
Download .patchdiff --git a/CLAUDE.md b/CLAUDE.md --- a/CLAUDE.md +++ b/CLAUDE.md @@ -384,1 +384,0 @@ -1. **Update CLAUDE.md** — ensure it reflects all changes made during the session
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.53.0. If the behavior is intended, declare it (host under permissions.network, a line in the README) instead of removing it; the next crawl scores declarations.
Issue / PR body
Title: mcp4acumatica: Contacted fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58, sparrow.cloudflare.com: not declared and not needed for the documented job (KillerSkills verdict blocked 23)
## What the honeypot observed KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8.1) and scored it **BLOCKED 23/100**. Summary: reads credential files, sends data to fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58, sparrow.cloudflare.com. - Contacted fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58, sparrow.cloudflare.com: not declared and not needed for the documented job. - Read ~/.npmrc in the decoy home directory. - A credential file was read and an undeclared host contacted in the same run. Full trace and findings: https://killerskills.ai/skills/glama/mcp4acumatica/0.53.0 ## Findings with a location - `CLAUDE.md:384` · Instructs the agent to modify its persistent memory or instruction files — CLAUDE.md:384 · Instructs the agent to modify its persistent memory or instruction files ## Proposed change The attached patch removes the 1 line above. If the behavior is intended, the fix is to declare it instead: list the host under `permissions.network` (or the MCP manifest) and say in the README why the package needs it; the next crawl will re-score it with the declaration taken into account. ## How this will be verified Nothing is "verified safe" by assertion. When a new version is published, KillerSkills re-runs it in the honeypot and the verdict page updates; you can trigger it early from the verdict page ("Re-scan after I publish a fix"). Reply here or at [email protected] if you believe the verdict is wrong; disputes are reviewed by a person and the outcome is published on the verdict page. _Proposed through killerskills.ai/threats by a user of the package, under their own GitHub account. The evidence is public; the package was never modified by KillerSkills._
# or from a terminal, under your own account: gh repo fork anilCopilot/mcp4acumaticaanil --clone && cd mcp4acumaticaanil curl -s https://killerskills.ai/skills/glama/mcp4acumatica/0.53.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/0.53.0 && git commit -am "mcp4acumatica: Contacted fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58, sparrow.cloudflare.com: not declared and not needed for the documented job" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/glama/mcp4acumatica/0.53.0/patch.md)
We count proposals opened, not merged: a merge shows up as a new version that the crawl re-runs. Disputes: the maintainer can contest the verdict from its page; a person reviews it and the outcome is published.