Propose a patch

Evidence

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

diff --git a/test/guards/base-url.test.ts b/test/guards/base-url.test.ts
--- a/test/guards/base-url.test.ts
+++ b/test/guards/base-url.test.ts
@@ -53,1 +53,0 @@
-['a user name and password', `https://admin:${PASSWORD}@bwat.example/v1`, /must not contain credentials/],
@@ -54,1 +53,0 @@
-['credentials on loopback', `http://admin:${PASSWORD}@127.0.0.1:8080/v1`, /must not contain credentials/],
@@ -63,1 +61,0 @@
-const value = `https://admin:${PASSWORD}[email protected]/v1`;
@@ -86,1 +83,0 @@
-['a base URL with credentials in it', `https://user:${PASSWORD}@bwat.example/v1`],

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.8.1. 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: bwat: URL with embedded credentials (KillerSkills verdict caution 78)

## 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 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/glama/bwat/0.8.1

## Findings with a location
- `test/guards/base-url.test.ts:63` · URL with embedded credentials — test/guards/base-url.test.ts:63 · URL with embedded credentials — may be phishing or credential leaking
- `test/guards/base-url.test.ts:54` · URL with embedded credentials — test/guards/base-url.test.ts:54 · URL with embedded credentials — may be phishing or credential leaking
- `test/guards/base-url.test.ts:86` · URL with embedded credentials — test/guards/base-url.test.ts:86 · URL with embedded credentials — may be phishing or credential leaking
- `test/guards/base-url.test.ts:53` · URL with embedded credentials — test/guards/base-url.test.ts:53 · URL with embedded credentials — may be phishing or credential leaking

## 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._