film-completeness
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external project data, which creates a potential surface for indirect prompt injection.
- Ingestion points: The agent reads the file
../../references/FILM_COMPLETENESS_AUDIT.mdand durable project state files to inform its decisions. - Boundary markers: The skill does not define specific delimiters or instructions to ignore commands embedded within the external data sources.
- Capability inventory: The skill utilizes a local script (
../../scripts/completeness_audit.py) and has the capability to write feature-scale state back to durable project files. - Sanitization: No explicit evidence of input validation or sanitization for the ingested reference data was found in the instructions.
- [SAFE]: The skill defines a structured workflow using project-local resources and scripts that align with its stated purpose. No unauthorized network activity, credential theft, or remote code execution patterns were detected.
Audit Metadata