Propose a patch

Evidence

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

diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -60,1 +60,0 @@
-### 2. Edit MEMORY.md
@@ -67,1 +66,0 @@
-### 3. Add to your AGENTS.md
diff --git a/demo/HEARTBEAT.md b/demo/HEARTBEAT.md
--- a/demo/HEARTBEAT.md
+++ b/demo/HEARTBEAT.md
@@ -18,1 +18,0 @@
-- For each entry: write notable ones to daily notes, update MEMORY.md if significant
@@ -35,1 +34,0 @@
-- Append to MEMORY.md
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -81,1 +81,0 @@
-6. If significant events occurred, append a summary to MEMORY.md under relevant sections
diff --git a/templates/cron-inbox.md b/templates/cron-inbox.md
--- a/templates/cron-inbox.md
+++ b/templates/cron-inbox.md
@@ -29,1 +29,0 @@
-3. If significant, update `MEMORY.md`
diff --git a/scripts/memory-extract.sh b/scripts/memory-extract.sh
--- a/scripts/memory-extract.sh
+++ b/scripts/memory-extract.sh
@@ -90,1 +90,0 @@
-# Append to MEMORY.md
diff --git a/templates/HEARTBEAT.md b/templates/HEARTBEAT.md
--- a/templates/HEARTBEAT.md
+++ b/templates/HEARTBEAT.md
@@ -21,1 +21,0 @@
-- If significant → update MEMORY.md
@@ -51,1 +50,0 @@
-- Append to MEMORY.md under relevant sections
diff --git a/scripts/install.sh b/scripts/install.sh
--- a/scripts/install.sh
+++ b/scripts/install.sh
@@ -143,1 +143,0 @@
-echo "1. Edit MEMORY.md with your personal context and preferences"
@@ -145,1 +144,0 @@
-echo "3. Add these lines to your AGENTS.md or session startup:"

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: clawmem-pro: 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/clawmem-pro/1.0.0

## Findings with a location
- `README.md:67` · Instructs the agent to modify its persistent memory or instruction files — README.md:67 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:60` · Instructs the agent to modify its persistent memory or instruction files — README.md:60 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `demo/HEARTBEAT.md:18` · Instructs the agent to modify its persistent memory or instruction files — demo/HEARTBEAT.md:18 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `demo/HEARTBEAT.md:35` · Instructs the agent to modify its persistent memory or instruction files — demo/HEARTBEAT.md:35 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `SKILL.md:81` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:81 · Instructs the agent to modify its persistent memory or instruction files
- `templates/cron-inbox.md:29` · Instructs the agent to modify its persistent memory or instruction files — templates/cron-inbox.md:29 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/memory-extract.sh:90` · Instructs the agent to modify its persistent memory or instruction files — scripts/memory-extract.sh:90 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `templates/HEARTBEAT.md:51` · Instructs the agent to modify its persistent memory or instruction files — templates/HEARTBEAT.md:51 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `templates/HEARTBEAT.md:21` · Instructs the agent to modify its persistent memory or instruction files — templates/HEARTBEAT.md:21 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/install.sh:145` · Instructs the agent to modify its persistent memory or instruction files — scripts/install.sh:145 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/install.sh:143` · Instructs the agent to modify its persistent memory or instruction files — scripts/install.sh:143 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 11 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._