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. 30 · Blocked
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 5 caught lines
Download .patchdiff --git a/USER/AISTEERINGRULES.md b/USER/AISTEERINGRULES.md --- a/USER/AISTEERINGRULES.md +++ b/USER/AISTEERINGRULES.md @@ -22,1 +22,0 @@ -Add your personal steering rules below. These override SYSTEM rules when there's a conflict. diff --git a/PAISECURITYSYSTEM/patterns.example.yaml b/PAISECURITYSYSTEM/patterns.example.yaml --- a/PAISECURITYSYSTEM/patterns.example.yaml +++ b/PAISECURITYSYSTEM/patterns.example.yaml @@ -130,1 +130,0 @@ -- "~/.ssh/id_*" @@ -132,1 +131,0 @@ -- "~/.aws/credentials" diff --git a/USER/PAISECURITYSYSTEM/patterns.yaml b/USER/PAISECURITYSYSTEM/patterns.yaml --- a/USER/PAISECURITYSYSTEM/patterns.yaml +++ b/USER/PAISECURITYSYSTEM/patterns.yaml @@ -178,1 +178,0 @@ -- "~/.ssh/id_*" @@ -180,1 +179,0 @@ -- "~/.aws/credentials"
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: pai: HTML comment carrying imperative instructions to the agent (KillerSkills verdict blocked 30)
## 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 30/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/pai/1.0.0 ## Findings with a location - `USER/AISTEERINGRULES.md:22` · HTML comment carrying imperative instructions to the agent — USER/AISTEERINGRULES.md:22 · HTML comment carrying imperative instructions to the agent - `PAISECURITYSYSTEM/patterns.example.yaml:130` · References a credential file in the home directory — PAISECURITYSYSTEM/patterns.example.yaml:130 · References a credential file in the home directory - `PAISECURITYSYSTEM/patterns.example.yaml:132` · References a credential file in the home directory — PAISECURITYSYSTEM/patterns.example.yaml:132 · References a credential file in the home directory - `USER/PAISECURITYSYSTEM/patterns.yaml:178` · References a credential file in the home directory — USER/PAISECURITYSYSTEM/patterns.yaml:178 · References a credential file in the home directory - `USER/PAISECURITYSYSTEM/patterns.yaml:180` · References a credential file in the home directory — USER/PAISECURITYSYSTEM/patterns.yaml:180 · References a credential file in the home directory ## Proposed change The attached patch removes the 5 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.