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. 61 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 2 caught lines
Download .patchdiff --git a/scripts/skill-audit.sh b/scripts/skill-audit.sh --- a/scripts/skill-audit.sh +++ b/scripts/skill-audit.sh @@ -198,1 +198,0 @@ -[11]="Do not modify agent config files (AGENTS.md, SOUL.md, etc.)." diff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -134,1 +134,0 @@ -| 11 | Agent config tampering | Write/modify AGENTS.md, SOUL.md, clawdbot.json |
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 2.0.9. 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: skillvet: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 61)
## 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 61/100**. Summary: no network, touches nothing outside the project, writes no memory. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/skillvet/2.0.9 ## Findings with a location - `scripts/skill-audit.sh:198` · Instructs the agent to modify its persistent memory or instruction files — scripts/skill-audit.sh:198 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:134` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:134 · Instructs the agent to modify its persistent memory or instruction files ## Proposed change The attached patch removes the 2 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.