Propose a patch

Evidence

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

diff --git a/dist/path-guard.js b/dist/path-guard.js
--- a/dist/path-guard.js
+++ b/dist/path-guard.js
@@ -5,1 +5,0 @@
-* ~/.ssh/id_rsa、.env、浏览器资料库当"素材"上传到 COS（公共可读 URL）。
@@ -11,1 +10,0 @@
-* 符号链接先解析再判（防 media.jpg -> ~/.ssh/id_rsa 绕过）。
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -124,1 +124,0 @@
-<summary><b>No Node / can't run npx?</b> (Coze, Dify, GPTs, custom agents)</summary> Drive the same pipeline over REST (`/v1/produce/*`) and paste [`SKILL.md`](

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.362. 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: References a credential file in the home directory (KillerSkills verdict caution 72)

## 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 72/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/mcp/0.1.362

## Findings with a location
- `dist/path-guard.js:11` · References a credential file in the home directory — dist/path-guard.js:11 · References a credential file in the home directory
- `README.md:124` · Collapsed <details> block carrying instructions — README.md:124 · Collapsed <details> block carrying instructions
- `dist/path-guard.js:5` · References a credential file in the home directory — dist/path-guard.js:5 · References a credential file in the home directory

## Proposed change
The attached patch removes the 3 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._