Propose a patch

Evidence

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

diff --git a/scripts/check-memory-host.py b/scripts/check-memory-host.py
--- a/scripts/check-memory-host.py
+++ b/scripts/check-memory-host.py
@@ -484,1 +484,0 @@
-results.append(check_file_exists(root, root / "AGENTS.md", "system_rules entry"))
@@ -485,1 +484,0 @@
-results.append(check_file_exists(root, root / "MEMORY.md", "long_term_memory file", required=False))
diff --git a/references/dreaming-integration.md b/references/dreaming-integration.md
--- a/references/dreaming-integration.md
+++ b/references/dreaming-integration.md
@@ -139,1 +139,0 @@
-- letting Dreaming write directly into `AGENTS.md` / `TOOLS.md` / `SOUL.md`

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.3.2. 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: memory-governor: 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 1.8.1) 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/memory-governor/0.3.2

## Findings with a location
- `scripts/check-memory-host.py:485` · Instructs the agent to modify its persistent memory or instruction files — scripts/check-memory-host.py:485 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/check-memory-host.py:484` · Instructs the agent to modify its persistent memory or instruction files — scripts/check-memory-host.py:484 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/dreaming-integration.md:139` · Instructs the agent to modify its persistent memory or instruction files — references/dreaming-integration.md:139 · 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._