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
@@ -88,1 +88,0 @@
-python3 engram/engram-rewire.py               # optional: slim MEMORY.md, add crons
diff --git a/install.sh b/install.sh
--- a/install.sh
+++ b/install.sh
@@ -213,1 +213,0 @@
-4. Optional — let Engram slim MEMORY.md and add its crons:
diff --git a/engine/engram-rewire.py b/engine/engram-rewire.py
--- a/engine/engram-rewire.py
+++ b/engine/engram-rewire.py
@@ -119,1 +119,0 @@
-"""Update AGENTS.md startup section to reference engram commands."""
@@ -205,1 +204,0 @@
-print("add an Engram section to AGENTS.md, and append 3 marked lines to your crontab.")
@@ -225,1 +223,0 @@
-# 3. Update AGENTS.md

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.2.3. 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: engram: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 66)

## 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 66/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/engram/1.2.3

## Findings with a location
- `README.md:88` · Instructs the agent to modify its persistent memory or instruction files — README.md:88 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `install.sh:213` · Instructs the agent to modify its persistent memory or instruction files — install.sh:213 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `engine/engram-rewire.py:205` · Instructs the agent to modify its persistent memory or instruction files — engine/engram-rewire.py:205 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `engine/engram-rewire.py:225` · Instructs the agent to modify its persistent memory or instruction files — engine/engram-rewire.py:225 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `engine/engram-rewire.py:119` · Instructs the agent to modify its persistent memory or instruction files — engine/engram-rewire.py:119 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## 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._