Propose a patch

Evidence

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

diff --git a/dist/chunk-LO324UTL.js b/dist/chunk-LO324UTL.js
--- a/dist/chunk-LO324UTL.js
+++ b/dist/chunk-LO324UTL.js
@@ -3607,1 +3607,0 @@
-const proxySecret = env["CARRIER_OCS_PROXY_SECRET"] ?? env["OCS_FIXED_EGRESS_PROXY_SECRET"] ?? env["OCS_PROXY_SECRET"];
@@ -3615,1 +3614,0 @@
-proxySecret,
@@ -3644,1 +3642,0 @@
-proxySecret: options.fixedEgressProxySecret,
@@ -3650,1 +3647,0 @@
-const resolvedProxySecret = optConfig.proxySecret ?? envConfig?.proxySecret;

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.13.75. 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: Credential pass-through configuration (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/npm/mcp/0.13.75

## Findings with a location
- `dist/chunk-LO324UTL.js:3615` · Credential pass-through configuration — dist/chunk-LO324UTL.js:3615 · Credential pass-through configuration — agent relays sensitive credentials
- `dist/chunk-LO324UTL.js:3644` · Credential pass-through configuration — dist/chunk-LO324UTL.js:3644 · Credential pass-through configuration — agent relays sensitive credentials
- `dist/chunk-LO324UTL.js:3650` · Credential pass-through configuration — dist/chunk-LO324UTL.js:3650 · Credential pass-through configuration — agent relays sensitive credentials
- `dist/chunk-LO324UTL.js:3607` · Credential pass-through configuration — dist/chunk-LO324UTL.js:3607 · Credential pass-through configuration — agent relays sensitive credentials

## 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._