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. 71 · Caution
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 @@ -139,1 +139,0 @@ -### Add reference to agent files AGENTS.md, CLAUDE.md, or .github/copilot-instructions.md to remind yourself to log learnings. (this is an alternative to hook-based reminders) @@ -309,1 +308,0 @@ -- Add `**Promoted**: CLAUDE.md`, `AGENTS.md`, or `.github/copilot-instructions.md` @@ -343,1 +341,0 @@ -- Missing automation (→ add to AGENTS.md) @@ -468,1 +465,0 @@ -7. **Promote aggressively** - if in doubt, add to CLAUDE.md or .github/copilot-instructions.md
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: super-self-improving-agent: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 71)
## 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 71/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/super-self-improving-agent/1.0.0 ## Findings with a location - `SKILL.md:309` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:309 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:139` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:139 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:468` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:468 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:343` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:343 · Instructs the agent to modify its persistent memory or instruction files ## 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._
# or from a terminal, under your own account: gh repo fork peterskoett/self-improving-agent --clone && cd self-improving-agent curl -s https://killerskills.ai/skills/clawhub/super-self-improving-agent/1.0.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.0 && git commit -am "super-self-improving-agent: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/super-self-improving-agent/1.0.0/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.