write-tech-spec

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill focuses on structured document creation and follows standard practices for codebase research and documentation.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes external data (codebase and PRODUCT.md), this is essential for its primary function. The risk is considered negligible as it operates on local project files within a development context.
  • Ingestion points: Reads local PRODUCT.md files and the project codebase.
  • Boundary markers: Not explicitly defined, but the instructions anchor the output to specific documentation structures.
  • Capability inventory: Uses gh CLI and Linear MCP tools for ticket management, and writes technical specs to the local filesystem.
  • Sanitization: Relies on the agent's standard code analysis and writing capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 04:18 PM