Propose a patch

Evidence

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

diff --git a/scripts/audit_diagnose.py b/scripts/audit_diagnose.py
--- a/scripts/audit_diagnose.py
+++ b/scripts/audit_diagnose.py
@@ -77,1 +77,0 @@
-'fix': 'Create memory_gc.py: scan recent N days of logs, extract candidates for MEMORY.md update.',
@@ -97,1 +96,0 @@
-'fix': 'Add routing table to AGENTS.md: articles→references/, Q&A→aiwiki, decisions→MEMORY.md, etc.',
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -89,1 +89,0 @@
-- Update MEMORY.md if project status changed

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.2.0. 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: workspace-audit: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 69)

## 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 69/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/workspace-audit/1.2.0

## Findings with a location
- `scripts/audit_diagnose.py:97` · Instructs the agent to modify its persistent memory or instruction files — scripts/audit_diagnose.py:97 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `SKILL.md:89` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:89 · Instructs the agent to modify its persistent memory or instruction files
- `scripts/audit_diagnose.py:77` · Instructs the agent to modify its persistent memory or instruction files — scripts/audit_diagnose.py:77 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 3 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._