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. 63 · 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
@@ -33,1 +33,0 @@
-**Integration** — add to your `AGENTS.md`:
@@ -54,1 +53,0 @@
-# Pass token delta from the current conversation
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -140,1 +140,0 @@
-Add to your `AGENTS.md` to enable the easter egg:
diff --git a/dashboard/src/App.tsx b/dashboard/src/App.tsx
--- a/dashboard/src/App.tsx
+++ b/dashboard/src/App.tsx
@@ -1,1 +1,0 @@
-import { useEffect, useRef, useState } from 'react'
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 3.0.0. 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: claw-rpg: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 63)
## 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 63/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/claw-rpg/3.0.0 ## Findings with a location - `SKILL.md:33` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:33 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:54` · Credential pass-through configuration — SKILL.md:54 · Credential pass-through configuration — agent relays sensitive credentials - `README.md:140` · Instructs the agent to modify its persistent memory or instruction files — README.md:140 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `dashboard/src/App.tsx:1` · Hidden zero-width characters detected — dashboard/src/App.tsx:1 · Hidden zero-width characters detected — may conceal content ## 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 RAMBOXIE/RAMBOXIE-claw-rpg --clone && cd RAMBOXIE-claw-rpg curl -s https://killerskills.ai/skills/clawhub/claw-rpg/3.0.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/3.0.0 && git commit -am "claw-rpg: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/claw-rpg/3.0.0/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.