Propose a patch

Evidence

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

diff --git a/dist/redact.js b/dist/redact.js
--- a/dist/redact.js
+++ b/dist/redact.js
@@ -104,1 +104,0 @@
-* holds `@`, `#` or `?` may also hold the real host (`https://deploy:443#@api.example.test` goes to host
diff --git a/dist/seatbelt-deploy.js b/dist/seatbelt-deploy.js
--- a/dist/seatbelt-deploy.js
+++ b/dist/seatbelt-deploy.js
@@ -279,1 +279,0 @@
-* env or the same command) is added to ~/.kube/config, never substituted for

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 3.9.112. 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: URL with embedded credentials (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: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/mcp/3.9.112

## Findings with a location
- `dist/redact.js:104` · URL with embedded credentials — dist/redact.js:104 · URL with embedded credentials — may be phishing or credential leaking
- `dist/seatbelt-deploy.js:279` · References a credential file in the home directory — dist/seatbelt-deploy.js:279 · References a credential file in the home directory

## 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._