← wip-repos@1.9.72

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 2 caught lines

Download .patch
diff --git a/claude.mjs b/claude.mjs
--- a/claude.mjs
+++ b/claude.mjs
@@ -118,1 +118,0 @@
-* Update the ecosystem section in a CLAUDE.md file.
@@ -238,1 +237,0 @@
-console.log(`  [update] ${repoName}/CLAUDE.md (${relevant.length} related repos)`);

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.9.72. 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: wip-repos: 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/wip-repos/1.9.72

## Findings with a location
- `claude.mjs:118` · Instructs the agent to modify its persistent memory or instruction files — claude.mjs:118 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `claude.mjs:238` · Instructs the agent to modify its persistent memory or instruction files — claude.mjs:238 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 2 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 wipcomputer/wip-ai-devops-toolbox --clone && cd wip-ai-devops-toolbox
curl -s https://killerskills.ai/skills/clawhub/wip-repos/1.9.72/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/1.9.72 && git commit -am "wip-repos: Instructs the agent to modify its persistent memory or instruction files"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/wip-repos/1.9.72/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.