Propose a patch

Evidence

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

diff --git a/src/nuvel_mcp/server.py b/src/nuvel_mcp/server.py
--- a/src/nuvel_mcp/server.py
+++ b/src/nuvel_mcp/server.py
@@ -296,1 +296,0 @@
-credentials (``https://user:pass@host``) that exception messages echo.
diff --git a/tests/test_health_runs.py b/tests/test_health_runs.py
--- a/tests/test_health_runs.py
+++ b/tests/test_health_runs.py
@@ -176,1 +176,0 @@
-URL = f"https://user:{SECRET}@relay.example/feedback"
diff --git a/tests/test_masking.py b/tests/test_masking.py
--- a/tests/test_masking.py
+++ b/tests/test_masking.py
@@ -301,1 +301,0 @@
-"hablé con pe‍dro",                 # zero-width joiner inside the name
@@ -302,1 +301,0 @@
-"hablé con pe​dro",                 # zero-width space
@@ -308,1 +306,0 @@
-"hablé con pedro­",                 # soft hyphen
@@ -641,1 +638,0 @@
-"x​y",

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.5.0. 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: nuvel-mcp: URL with embedded credentials (KillerSkills verdict caution 55)

## 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 55/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/nuvel-mcp/0.5.0

## Findings with a location
- `src/nuvel_mcp/server.py:296` · URL with embedded credentials — src/nuvel_mcp/server.py:296 · URL with embedded credentials — may be phishing or credential leaking
- `tests/test_health_runs.py:176` · URL with embedded credentials — tests/test_health_runs.py:176 · URL with embedded credentials — may be phishing or credential leaking
- `tests/test_masking.py:641` · Hidden zero-width characters detected — tests/test_masking.py:641 · Hidden zero-width characters detected — may conceal content
- `tests/test_masking.py:301` · Hidden zero-width characters detected — tests/test_masking.py:301 · Hidden zero-width characters detected — may conceal content
- `tests/test_masking.py:308` · Hidden zero-width characters detected — tests/test_masking.py:308 · Hidden zero-width characters detected — may conceal content
- `tests/test_masking.py:302` · Hidden zero-width characters detected — tests/test_masking.py:302 · Hidden zero-width characters detected — may conceal content

## Proposed change
The attached patch removes the 6 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._