best-practices
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a multi-phase research and planning process designed to ensure accuracy and adherence to current documentation and codebase conventions.
- [PROMPT_INJECTION]: Assessment of indirect prompt injection surface associated with the skill's research function.
- Ingestion points: The skill instructs the agent to use WebSearch and WebFetch tools in Phase 1 to gather external information, alongside Grep and Glob for local codebase context.
- Boundary markers: Research findings are synthesized into a structured 'Research Summary' using markdown headers and templates.
- Capability inventory: The skill utilizes web retrieval and filesystem search tools.
- Sanitization: Security and accuracy are maintained through 'HARD-GATE' instructions that necessitate explicit user approval of both the research findings and the proposed plan before any execution or file modifications occur.
Audit Metadata