thorough-plan
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, providing a workflow for agents to follow during complex tasks. It does not contain any scripts, binary executables, or commands that interact with the host system directly.
- [SAFE]: No instances of prompt injection, obfuscation, or credential exposure were found. The skill follows best practices for guiding agent behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill acknowledges an attack surface by processing user 'briefs' and external 'research' data.
- Ingestion points: User-provided task descriptions (briefs) and external research data from tools like 'exa' or 'web search'.
- Boundary markers: None explicitly defined in the workflow instructions.
- Capability inventory: Uses 'Explore' and 'research' agents to gather codebase and web context.
- Sanitization: No specific sanitization or filtering logic is provided for external data.
Audit Metadata