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-card.md b/skill-card.md --- a/skill-card.md +++ b/skill-card.md @@ -53,1 +53,0 @@ -**Other Properties Related to Output:** [May create or update PROMPT.md, AGENTS.md, IMPLEMENTATION_PLAN.md, and specs files during a Ralph Loop workflow.] diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -133,1 +133,0 @@ -- Write AGENTS.md with test commands @@ -247,1 +246,0 @@ -6) Update AGENTS.md with today's learnings diff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -164,1 +164,0 @@ -6) Update AGENTS.md with learnings
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.1.0. 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: ralph-loop-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 1.9.2) 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/ralph-loop-agent/1.1.0 ## Findings with a location - `skill-card.md:53` · Instructs the agent to modify its persistent memory or instruction files — skill-card.md:53 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `README.md:133` · Instructs the agent to modify its persistent memory or instruction files — README.md:133 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `README.md:247` · Instructs the agent to modify its persistent memory or instruction files — README.md:247 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:164` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:164 · 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 addozhang/openclaw-forge --clone && cd openclaw-forge curl -s https://killerskills.ai/skills/clawhub/ralph-loop-agent/1.1.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.1.0 && git commit -am "ralph-loop-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/ralph-loop-agent/1.1.0/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.