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. 69 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 4 caught lines
Download .patchdiff --git a/templates/platforms/claude-knowledge.md b/templates/platforms/claude-knowledge.md --- a/templates/platforms/claude-knowledge.md +++ b/templates/platforms/claude-knowledge.md @@ -3,1 +3,0 @@ -<context> @@ -7,1 +6,0 @@ -</context> @@ -9,1 +7,0 @@ -<rules> @@ -55,1 +52,0 @@ -</rules>
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: clean-code-review: Fake instruction boundary tag (KillerSkills verdict caution 69)
## 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 **CAUTION 69/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/clean-code-review/1.0.0 ## Findings with a location - `templates/platforms/claude-knowledge.md:55` · Fake instruction boundary tag — templates/platforms/claude-knowledge.md:55 · Fake instruction boundary tag · informational: not an instruction file - `templates/platforms/claude-knowledge.md:9` · Fake instruction boundary tag — templates/platforms/claude-knowledge.md:9 · Fake instruction boundary tag · informational: not an instruction file - `templates/platforms/claude-knowledge.md:3` · Fake instruction boundary tag — templates/platforms/claude-knowledge.md:3 · Fake instruction boundary tag · informational: not an instruction file - `templates/platforms/claude-knowledge.md:7` · Fake instruction boundary tag — templates/platforms/claude-knowledge.md:7 · Fake instruction boundary tag · informational: not an instruction file ## Proposed change The attached patch removes the 4 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._
# or from a terminal, under your own account: gh repo fork wpank/ai --clone && cd ai curl -s https://killerskills.ai/skills/clawhub/clean-code-review/1.0.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.0 && git commit -am "clean-code-review: Fake instruction boundary tag" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/clean-code-review/1.0.0/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.