Propose a patch

Evidence

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

diff --git a/scripts/sync.js b/scripts/sync.js
--- a/scripts/sync.js
+++ b/scripts/sync.js
@@ -16,1 +16,0 @@
-//   syncKnowledgeCard(card)              — write-back to MEMORY.md
@@ -94,1 +93,0 @@
-* Append a knowledge card to MEMORY.md.
@@ -129,1 +127,0 @@
-// 2. If insights contain knowledge cards, also write to MEMORY.md
diff --git a/scripts/import.js b/scripts/import.js
--- a/scripts/import.js
+++ b/scripts/import.js
@@ -164,1 +164,0 @@
-process.stderr.write(`[awareness-import] Found ${entries.length} entries in MEMORY.md\n`);

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.3.11. 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: awareness-memory: 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/awareness-memory/0.3.11

## Findings with a location
- `scripts/sync.js:94` · Instructs the agent to modify its persistent memory or instruction files — scripts/sync.js:94 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/sync.js:129` · Instructs the agent to modify its persistent memory or instruction files — scripts/sync.js:129 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/sync.js:16` · Instructs the agent to modify its persistent memory or instruction files — scripts/sync.js:16 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/import.js:164` · Instructs the agent to modify its persistent memory or instruction files — scripts/import.js:164 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## 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._