connected-chrome
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of documentation and instructions for using existing agent capabilities. No malicious scripts, hardcoded credentials, or obfuscated payloads were found.
- [INDIRECT_PROMPT_INJECTION]: The skill exposes the agent to external web data through the Chrome integration.
- Ingestion points: User-facing Chrome browser profiles and open tabs (SKILL.md).
- Boundary markers: None explicitly defined in the skill markdown.
- Capability inventory: Profile access, extension interaction, and tab management (SKILL.md).
- Sanitization: Provided by the platform's browser integration implementation.
Audit Metadata