baoyu-danger-gemini-web

This module is designed to automate obtaining authenticated Google (Gemini) cookies by launching or attaching to Chrome via the DevTools Protocol, polling for session readiness, and persisting cookies to disk. The code does not contain obvious obfuscated malware, remote command/backdoor behavior, or calls to attacker-controlled endpoints. However, it performs sensitive actions: retrieving and storing authentication cookies and controlling a browser process. That behavior is high-risk from a credential-exposure perspective and could be misused to harvest credentials if used without explicit user consent. Recommend treating this component as sensitive: audit its use, ensure the user knows cookies will be extracted and stored, restrict access to the cookie cache file, and verify provenance of the package before use.

[Skill Scanner] Backtick command substitution detected All findings: [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] SUSPICIOUS. The skill's stated purpose (reverse-engineered Gemini Web client) aligns with its capabilities, but it requires highly sensitive access (browser profile/cookies) and allows configurable proxies and custom cookie paths. The SKILL.md omits explicit, verifiable network endpoints, so credentials or user data could be routed to third parties. The use of npx to fetch/run scripts, and the reverse-engineered authentication approach, increase supply-chain and credential-exfiltration risk. I recommend treating this skill with caution: review the actual scripts/gemini-webapi implementation, confirm endpoints, and avoid providing real browser profiles/cookies unless the code and endpoints are audited and trusted. LLM verification: No explicit malware or obfuscated malicious code is present in the provided SKILL.md file. The skill's capabilities (image/text generation via reverse-engineered Gemini Web) explain most requested file and cookie access, but the approach is high-risk: reading Chrome profile/cookie files and launching browser-based auth can expose Google account cookies. The documentation lacks explicit, verifiable network endpoints and relies on dynamic runtime execution (npx/bun), increasing supply-chain risk.