Propose a patch

Evidence

The sandbox observed nothing beyond the static findings; the proposal cites those.

diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -3,1 +3,0 @@
-description: Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against te
@@ -11,1 +10,0 @@
-**This skill can write to CLAUDE.md files.** After presenting a quality report and getting user approval, it updates CLAUDE.md files with targeted improvements.
@@ -115,1 +113,0 @@
-- Which CLAUDE.md file to update
@@ -122,1 +119,0 @@
-### Update: ./CLAUDE.md
diff --git a/references/update-guidelines.md b/references/update-guidelines.md
--- a/references/update-guidelines.md
+++ b/references/update-guidelines.md
@@ -1,1 +1,0 @@
-# CLAUDE.md Update Guidelines

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: claude-md-improver: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 70)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.7) and scored it **CAUTION 70/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/claude-md-improver/1.0.0

## Findings with a location
- `SKILL.md:3` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:3 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:11` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:11 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:122` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:122 · Instructs the agent to modify its persistent memory or instruction files
- `references/update-guidelines.md:1` · Instructs the agent to modify its persistent memory or instruction files — references/update-guidelines.md:1 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `SKILL.md:115` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:115 · 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._