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. 67 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 5 caught lines
Download .patchdiff --git a/assets/workspace/AGENTS.md b/assets/workspace/AGENTS.md --- a/assets/workspace/AGENTS.md +++ b/assets/workspace/AGENTS.md @@ -23,1 +23,0 @@ -7. Never create or modify AGENTS.md again just because the user repeats this preference. Treat this rule as persistent. @@ -61,1 +60,0 @@ -- You can **read, edit, and update** MEMORY.md freely in main sessions @@ -64,1 +62,0 @@ -- Over time, review your daily files and update MEMORY.md with what's worth keeping @@ -71,1 +68,0 @@ -- When you learn a lesson → update AGENTS.md, TOOLS.md, or the relevant skill @@ -268,1 +264,0 @@ -- **Review and update MEMORY.md** (see below)
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.5.0. 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: openclaw-continuity-pack: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 67)
## What the honeypot observed KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.9.2) and scored it **CAUTION 67/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/openclaw-continuity-pack/0.5.0 ## Findings with a location - `assets/workspace/AGENTS.md:268` · Instructs the agent to modify its persistent memory or instruction files — assets/workspace/AGENTS.md:268 · Instructs the agent to modify its persistent memory or instruction files - `assets/workspace/AGENTS.md:23` · Instructs the agent to modify its persistent memory or instruction files — assets/workspace/AGENTS.md:23 · Instructs the agent to modify its persistent memory or instruction files - `assets/workspace/AGENTS.md:61` · Instructs the agent to modify its persistent memory or instruction files — assets/workspace/AGENTS.md:61 · Instructs the agent to modify its persistent memory or instruction files - `assets/workspace/AGENTS.md:64` · Instructs the agent to modify its persistent memory or instruction files — assets/workspace/AGENTS.md:64 · Instructs the agent to modify its persistent memory or instruction files - `assets/workspace/AGENTS.md:71` · Instructs the agent to modify its persistent memory or instruction files — assets/workspace/AGENTS.md:71 · Instructs the agent to modify its persistent memory or instruction files ## 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.