Propose a patch

Evidence

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

diff --git a/src/mcp_auditor/graph/prompts.py b/src/mcp_auditor/graph/prompts.py
--- a/src/mcp_auditor/graph/prompts.py
+++ b/src/mcp_auditor/graph/prompts.py
@@ -14,1 +14,0 @@
-- To prove an injection landed, prefer evidence of what it reaches: read something whose disclosure would matter, a credential or configuration file (`.env`, `~/.ssh/id_rsa`, a cloud credential direct
diff --git a/CLAUDE.md b/CLAUDE.md
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -93,1 +93,0 @@
-- **Update the living docs as part of the change, not after.** When an implementation adds or changes a command, prerequisite, env var, CLI flag, or user-facing behavior, update the living docs in the

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.4.0. 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: mcp-auditor: References a credential file in the home directory (KillerSkills verdict caution 45)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.7) and scored it **CAUTION 45/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mcp-auditor/0.4.0

## Findings with a location
- `src/mcp_auditor/graph/prompts.py:14` · References a credential file in the home directory — src/mcp_auditor/graph/prompts.py:14 · References a credential file in the home directory
- `CLAUDE.md:93` · Instructs the agent to modify its persistent memory or instruction files — CLAUDE.md:93 · Instructs the agent to modify its persistent memory or instruction files

## Proposed change
The attached patch removes the 2 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._