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 2 caught lines
Download .patchdiff --git a/references/paste-prompt.md b/references/paste-prompt.md --- a/references/paste-prompt.md +++ b/references/paste-prompt.md @@ -30,1 +30,0 @@ -7. Write AGENTS.md with these rules for every later session: save a version after each finished step; update media.lock.jsonl and diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -1,1 +1,0 @@ -Generated by .github/readme/build.ts from SKILL.md files and .github/readme/*.json. Edit those and run `bun .github/readme/build.ts`; CI fails when this file is
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.2. 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: video-project-github: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 72)
## What the honeypot observed KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.7) and scored it **CAUTION 72/100**. Summary: no network, touches nothing outside the project, writes no memory. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/video-project-github/1.0.2 ## Findings with a location - `references/paste-prompt.md:30` · Instructs the agent to modify its persistent memory or instruction files — references/paste-prompt.md:30 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file · informational: not an instruction file - `README.md:1` · HTML comment carrying imperative instructions to the agent — README.md:1 · HTML comment carrying imperative instructions to the agent ## 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._
# or from a terminal, under your own account: gh repo fork vargHQ/skills --clone && cd skills curl -s https://killerskills.ai/skills/clawhub/video-project-github/1.0.2/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.2 && git commit -am "video-project-github: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/video-project-github/1.0.2/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.