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. 72 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 3 caught lines
Download .patchdiff --git a/prd-template.md b/prd-template.md --- a/prd-template.md +++ b/prd-template.md @@ -148,1 +148,0 @@ -- GIVEN <context> WHEN <action> THEN <expected result> @@ -149,1 +148,0 @@ -- GIVEN <context> WHEN <edge case> THEN <expected handling> @@ -155,1 +153,0 @@ -- GIVEN <context> WHEN <action> THEN <expected result>
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: prd-for-ai-agents: Fake instruction boundary tag (KillerSkills verdict caution 72)
## What the honeypot observed KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.9.2) and scored it **CAUTION 72/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/prd-for-ai-agents/1.0.0 ## Findings with a location - `prd-template.md:148` · Fake instruction boundary tag — prd-template.md:148 · Fake instruction boundary tag · informational: not an instruction file - `prd-template.md:149` · Fake instruction boundary tag — prd-template.md:149 · Fake instruction boundary tag · informational: not an instruction file - `prd-template.md:155` · Fake instruction boundary tag — prd-template.md:155 · Fake instruction boundary tag · informational: not an instruction file ## Proposed change The attached patch removes the 3 lines 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._
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.