lazyweb-add-inspo-source
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill locates and executes a local automation binary ('browse') found within the user's home directory or project subdirectories. This tool is used to automate browser interactions for research tasks.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes snapshots from external websites. 1. Ingestion points: Browser snapshots of external sites in SKILL.md. 2. Boundary markers: None explicitly defined in the instructions. 3. Capability inventory: Bash, Read, Write, and execution of the local browse binary. 4. Sanitization: No visible sanitization is performed on the captured site content.
- [SAFE]: The authentication process uses a handoff mechanism that allows the user to log in manually, which is a security best practice for managing sensitive credentials in AI environments.
Audit Metadata