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
@@ -116,1 +116,0 @@
-**3. Add agent hook to `CLAUDE.md`:**
diff --git a/PKG-INFO b/PKG-INFO
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -163,1 +163,0 @@
-**3. Add agent hook to `CLAUDE.md`:**
diff --git a/neural_memory/cli.py b/neural_memory/cli.py
--- a/neural_memory/cli.py
+++ b/neural_memory/cli.py
@@ -328,1 +328,0 @@
-print("Add neural-memory agent hook to CLAUDE.md?")
diff --git a/neural_memory_mcp.egg-info/PKG-INFO b/neural_memory_mcp.egg-info/PKG-INFO
--- a/neural_memory_mcp.egg-info/PKG-INFO
+++ b/neural_memory_mcp.egg-info/PKG-INFO
@@ -163,1 +163,0 @@
-**3. Add agent hook to `CLAUDE.md`:**

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.9.0. 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: neural-memory-mcp: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 78)

## 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 78/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/neural-memory-mcp/0.9.0

## Findings with a location
- `README.md:116` · Instructs the agent to modify its persistent memory or instruction files — README.md:116 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `PKG-INFO:163` · Instructs the agent to modify its persistent memory or instruction files — PKG-INFO:163 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `neural_memory/cli.py:328` · Instructs the agent to modify its persistent memory or instruction files — neural_memory/cli.py:328 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `neural_memory_mcp.egg-info/PKG-INFO:163` · Instructs the agent to modify its persistent memory or instruction files — neural_memory_mcp.egg-info/PKG-INFO:163 · 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._