feature-spec-author

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a well-defined documentation authoring workflow using internal templates and mandatory user approval gates (requirements, design, and tasks) before artifacts are finalized.
  • [SAFE]: External publishing is restricted to well-known documentation services (Confluence, Notion, Azure DevOps) using an abstract adapter pattern and standard MCP tools, which is consistent with the skill's primary purpose.
  • [SAFE]: File system access is limited to the project's documentation and steering directories, used for maintaining technical context and persisting spec documents.
  • [SAFE]: The skill minimizes its own capability footprint by delegating complex specialized analysis (such as architectural design or ontology) to other trusted internal skills within the platform ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 01:23 PM
Security Audit — agent-trust-hub — feature-spec-author