gsd-ingest-docs

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external documentation from the repository to synthesize planning files, which is an inherent surface for indirect prompt injection.
  • Ingestion points: Reads ADRs, PRDs, SPECs, and RFCs from the repository (e.g., docs/adr/, docs/prd/).
  • Boundary markers: Utilizes a conflict engine and approval gates (discovery, conflict report) to review content before writing to the .planning/ directory.
  • Capability inventory: Employs Read, Write, Edit, Bash, and Agent tools for document management.
  • Sanitization: Applies a strict precedence rule (ADR > SPEC > PRD > DOC) and blocks file generation if unresolved contradictions are detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:38 PM
Security Audit — agent-trust-hub — gsd-ingest-docs