Propose a patch

Evidence

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

diff --git a/src/mcp_stealth_chrome/server.py b/src/mcp_stealth_chrome/server.py
--- a/src/mcp_stealth_chrome/server.py
+++ b/src/mcp_stealth_chrome/server.py
@@ -2040,1 +2040,0 @@
-proxy: "http://user:pass@host:port" or "socks5://host:port"
diff --git a/src/mcp_stealth_chrome/tools/research.py b/src/mcp_stealth_chrome/tools/research.py
--- a/src/mcp_stealth_chrome/tools/research.py
+++ b/src/mcp_stealth_chrome/tools/research.py
@@ -188,1 +188,0 @@
-`export RESEARCH_PROXY=http://user:pass@host:port` and every fetch uses it.
diff --git a/src/mcp_stealth_chrome/tools/vision.py b/src/mcp_stealth_chrome/tools/vision.py
--- a/src/mcp_stealth_chrome/tools/vision.py
+++ b/src/mcp_stealth_chrome/tools/vision.py
@@ -264,1 +264,0 @@
-"ANTHROPIC_API_KEY, or pass api_key= to the tool."
diff --git a/src/mcp_stealth_chrome/tools/stealth.py b/src/mcp_stealth_chrome/tools/stealth.py
--- a/src/mcp_stealth_chrome/tools/stealth.py
+++ b/src/mcp_stealth_chrome/tools/stealth.py
@@ -106,1 +106,0 @@
-Needs CAPSOLVER_KEY env var (or pass api_key). Returns solved token.

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.15.2. 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: mcp-stealth-chrome: URL with embedded credentials (KillerSkills verdict caution 70)

## 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 70/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mcp-stealth-chrome/0.15.2

## Findings with a location
- `src/mcp_stealth_chrome/server.py:2040` · URL with embedded credentials — src/mcp_stealth_chrome/server.py:2040 · URL with embedded credentials — may be phishing or credential leaking
- `src/mcp_stealth_chrome/tools/research.py:188` · URL with embedded credentials — src/mcp_stealth_chrome/tools/research.py:188 · URL with embedded credentials — may be phishing or credential leaking
- `src/mcp_stealth_chrome/tools/vision.py:264` · Credential pass-through configuration — src/mcp_stealth_chrome/tools/vision.py:264 · Credential pass-through configuration — agent relays sensitive credentials
- `src/mcp_stealth_chrome/tools/stealth.py:106` · Credential pass-through configuration — src/mcp_stealth_chrome/tools/stealth.py:106 · Credential pass-through configuration — agent relays sensitive credentials

## 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._