Propose a patch

Evidence

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

diff --git a/build/base-url.js b/build/base-url.js
--- a/build/base-url.js
+++ b/build/base-url.js
@@ -37,1 +37,0 @@
-* `https://user:secret@host` can never reach an error string, usage text, or log.
diff --git a/build/plane/defaults.js b/build/plane/defaults.js
--- a/build/plane/defaults.js
+++ b/build/plane/defaults.js
@@ -431,1 +431,0 @@
-* - executor   → `body.executor.process_heartbeat.state` / `…​.last_seen_at`
diff --git a/build/agent-notes.js b/build/agent-notes.js
--- a/build/agent-notes.js
+++ b/build/agent-notes.js
@@ -100,1 +100,0 @@
-targets.add("AGENTS.md");
@@ -106,1 +105,0 @@
-targets.add("CLAUDE.md");

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.2.75. 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-server: 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-server/0.2.75

## Findings with a location
- `build/base-url.js:37` · URL with embedded credentials — build/base-url.js:37 · URL with embedded credentials — may be phishing or credential leaking
- `build/plane/defaults.js:431` · Hidden zero-width characters detected — build/plane/defaults.js:431 · Hidden zero-width characters detected — may conceal content
- `build/agent-notes.js:106` · Instructs the agent to modify its persistent memory or instruction files — build/agent-notes.js:106 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `build/agent-notes.js:100` · Instructs the agent to modify its persistent memory or instruction files — build/agent-notes.js:100 · 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._