project-adr
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for architectural documentation and follows standard practices for recording decisions. It does not attempt to access sensitive system files, hardcode credentials, or perform unauthorized network requests.- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an ingestion surface by reading local ADR files to identify conventions, however, the risk is negligible as the agent's capabilities are restricted to writing and linking markdown files.
- Ingestion points: The skill reads local ADR conventions and existing decisions as instructed in SKILL.md.
- Boundary markers: No explicit boundary markers or instruction-ignoring warnings are present.
- Capability inventory: The skill is limited to reading, creating, and updating local ADR records and index files.
- Sanitization: No specific sanitization or filtering of the ingested content is defined.
Audit Metadata