Propose a patch

Evidence

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

diff --git a/capguru_mcp/server.py b/capguru_mcp/server.py
--- a/capguru_mcp/server.py
+++ b/capguru_mcp/server.py
@@ -237,1 +237,0 @@
-fail('Proxy must look like http://login:password@host:port or login:password@host:port')
@@ -395,1 +394,0 @@
-proxy: 'http://login:password@host:port' or 'login:password@host:port' (socks5:// also works).
@@ -670,1 +668,0 @@
-proxy: same format as in open_browser ('http://login:password@host:port' or 'login:password@host:port').

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.3.5. 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: capguru-mcp: URL with embedded credentials (KillerSkills verdict caution 77)

## 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 77/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/capguru-mcp/0.3.5

## Findings with a location
- `capguru_mcp/server.py:237` · URL with embedded credentials — capguru_mcp/server.py:237 · URL with embedded credentials — may be phishing or credential leaking
- `capguru_mcp/server.py:395` · URL with embedded credentials — capguru_mcp/server.py:395 · URL with embedded credentials — may be phishing or credential leaking
- `capguru_mcp/server.py:670` · URL with embedded credentials — capguru_mcp/server.py:670 · URL with embedded credentials — may be phishing or credential leaking

## 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._