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. 39 · Blocked
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 4 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -69,1 +69,0 @@ -- Presence of `<system>`, `[INST]`, `[/INST]` XML/markup tags in external content @@ -75,1 +74,0 @@ -ignore @@ -92,1 +90,0 @@ -- Shell commands that pipe sensitive files to external tools: `cat ~/.ssh/id_rsa | curl` @@ -94,1 +91,0 @@ -- Reading any of `~/.ssh/`, `~/.aws/credentials`, `~/.config/`, keychain access — then immediately making a network request
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.3.0. 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: shoofly-advanced: HTML comment carrying imperative instructions to the agent (KillerSkills verdict blocked 39)
## 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 39/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/shoofly-advanced/1.3.0 ## Findings with a location - `SKILL.md:75` · HTML comment carrying imperative instructions to the agent — SKILL.md:75 · HTML comment carrying imperative instructions to the agent - `SKILL.md:94` · Reads credential paths from the home directory — SKILL.md:94 · Reads credential paths from the home directory - `SKILL.md:94` · References a credential file in the home directory — SKILL.md:94 · References a credential file in the home directory - `SKILL.md:69` · Fake instruction boundary tag — SKILL.md:69 · Fake instruction boundary tag - `SKILL.md:92` · Reads credential paths from the home directory — SKILL.md:92 · Reads credential paths from the home directory - `SKILL.md:92` · References a credential file in the home directory — SKILL.md:92 · References a credential file in the home directory ## 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._
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.