Propose a patch

Evidence

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

diff --git a/tools/simulator/test_serve.py b/tools/simulator/test_serve.py
--- a/tools/simulator/test_serve.py
+++ b/tools/simulator/test_serve.py
@@ -436,1 +436,0 @@
-for bad_url in ("ftp://a.example/x", "file:///etc/passwd", "https:///nohost", "https://user:[email protected]/"):
diff --git a/tests/test_cli.py b/tests/test_cli.py
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -908,1 +908,0 @@
-"https://u:[email protected]", "https://x.example:99999"]
diff --git a/deploy/tunnel.sh b/deploy/tunnel.sh
--- a/deploy/tunnel.sh
+++ b/deploy/tunnel.sh
@@ -11,1 +11,0 @@
-#   ./deploy/tunnel.sh -l 8766 -r 18766 -H server.example.com -u ubuntu -i ~/.ssh/id_ed25519

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0. 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: glasscast: URL with embedded credentials (KillerSkills verdict caution 68)

## 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 68/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/glasscast/0.1.0

## Findings with a location
- `tools/simulator/test_serve.py:436` · URL with embedded credentials — tools/simulator/test_serve.py:436 · URL with embedded credentials — may be phishing or credential leaking
- `tests/test_cli.py:908` · URL with embedded credentials — tests/test_cli.py:908 · URL with embedded credentials — may be phishing or credential leaking
- `deploy/tunnel.sh:11` · References a credential file in the home directory — deploy/tunnel.sh:11 · References a credential file in the home directory

## 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._