skills/dakdevs/skills/best-practices/Gen Agent Trust Hub

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
Risk Level
SAFE
Analyzed
Apr 21, 2026, 07:04 PM
Security Audit — agent-trust-hub — best-practices