reference-authority
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external file located at
../../references/REFERENCE_AUTHORITY.mdto guide 'reference-driven generation'. - Ingestion points:
../../references/REFERENCE_AUTHORITY.md(referenced in SKILL.md). - Boundary markers: None identified in the provided instructions to prevent the agent from obeying embedded commands within the reference file.
- Capability inventory: The skill executes a local script
scripts/reference_authority.py(referenced in SKILL.md). - Sanitization: No sanitization or verification of the external file's content is described.
Audit Metadata