write-tech-spec

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured guidance for generating technical documentation within a specific monorepo context.\n- [COMMAND_EXECUTION]: The skill references standard project commands (pnpm check, pnpm build:desktop) and the GitHub CLI (gh). These are used for validation and task management within the developer's workflow and are consistent with the skill's purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files like PRODUCT.md and project source code to inform the technical spec.\n
  • Ingestion points: Reads product specifications, ADRs, and source code files (e.g., apps/desktop, packages/editor) from the local filesystem.\n
  • Boundary markers: Not present for internal project documentation.\n
  • Capability inventory: Includes filesystem read/write access and the ability to execute project-specific shell commands (pnpm) and GitHub CLI operations.\n
  • Sanitization: None specified, relying on the agent's inherent safety filters when processing project data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 11:41 PM
Security Audit — agent-trust-hub — write-tech-spec