Security Audit

jimliu/baoyu-skills:skills/baoyu-danger-gemini-web

github.com/jimliu/baoyu-skills

AI SkillCommit 6b7a2e417500

CAUTION

Scanned 24 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

jimliu/baoyu-skills:skills/baoyu-danger-gemini-web received a trust score of 57/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 5 findings: 0 critical, 2 high, 2 medium, and 1 low severity. Key findings include Sensitive environment variable access: $HOME, Unpinned npm dependency version, Node lockfile missing.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on August 6, 2026 (commit 6b7a2e41). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

93%

Dependency Graph

91%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Filesystem Write

2 findings

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings5

Severity	Finding	Layer	Location
HIGH	Automated extraction of Google session cookies from browser The skill automatically attempts to connect to a running Chrome/Chromium instance via Chrome DevTools Protocol (CDP) or launch a new instance to extract sensitive Google session cookies (`__Secure-1PSID`, `__Secure-1PSIDTS`). This behavior is equivalent to session hijacking/credential harvesting, as it accesses and extracts highly sensitive authentication state from the user's browser without explicit, secure storage boundaries. Avoid extracting session cookies directly from the user's browser. Instead, prompt the user to securely provide an API key or manually input the required session tokens, and store them securely using the platform's credential storage.	LLM	scripts/gemini-webapi/utils/load-browser-cookies.ts:140
HIGH	Command Injection via unescaped Windows USERPROFILE in WSL environment The function `getWslWindowsHome` retrieves the Windows `USERPROFILE` environment variable using `execSync` and then passes the raw output directly into another `execSync` call (`wslpath -u "${raw}"`) without sanitization or escaping. If the `USERPROFILE` environment variable contains shell metacharacters or double quotes, this leads to arbitrary command execution in the WSL shell context. Avoid using shell execution (`execSync` with a string) to resolve paths. Use `execFileSync` or pass arguments as an array to prevent shell expansion and command injection, or sanitize the input thoroughly before execution.	LLM	scripts/gemini-webapi/utils/paths.ts:31
MEDIUM	Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated.	Static	skills/baoyu-danger-gemini-web/SKILL.md:58
MEDIUM	Unpinned npm dependency version Dependency 'baoyu-chrome-cdp' is not pinned to an exact version ('^0.1.1'). Pin dependencies to exact versions to reduce drift and supply-chain risk.	Dependencies	skills/baoyu-danger-gemini-web/scripts/package.json
LOW	Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution.	Dependencies	skills/baoyu-danger-gemini-web/scripts/package.json

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1c30fdf0a6edb0f8.svg)](https://skillshield.io/report/1c30fdf0a6edb0f8)