Propose a patch

Evidence

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

diff --git a/cli/src/report.rs b/cli/src/report.rs
--- a/cli/src/report.rs
+++ b/cli/src/report.rs
@@ -1746,1 +1746,0 @@
-let out = red("open https://user:[email protected]/x");
diff --git a/cli/src/output.rs b/cli/src/output.rs
--- a/cli/src/output.rs
+++ b/cli/src/output.rs
@@ -7231,1 +7231,0 @@
-Supports authenticated proxies: --proxy "http://user:[email protected]:7890"
diff --git a/cli/src/main.rs b/cli/src/main.rs
--- a/cli/src/main.rs
+++ b/cli/src/main.rs
@@ -5649,1 +5649,0 @@
-let result = parse_proxy("http://user:[email protected]:8080");
@@ -5687,1 +5686,0 @@
-let result = parse_proxy("http://user:p@ss:[email protected]:8080");

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.5.291. 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: chrome-use: 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/chrome-use/1.5.291

## Findings with a location
- `cli/src/report.rs:1746` · URL with embedded credentials — cli/src/report.rs:1746 · URL with embedded credentials — may be phishing or credential leaking
- `cli/src/output.rs:7231` · URL with embedded credentials — cli/src/output.rs:7231 · URL with embedded credentials — may be phishing or credential leaking
- `cli/src/main.rs:5687` · URL with embedded credentials — cli/src/main.rs:5687 · URL with embedded credentials — may be phishing or credential leaking
- `cli/src/main.rs:5649` · URL with embedded credentials — cli/src/main.rs:5649 · 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._