preview
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's operations are restricted to processing local configuration data and generating analysis files within the project's designated previews folder.
- [PROMPT_INJECTION]: The skill ingests data from 'interf.yaml', creating a surface for indirect prompt injection.
- Ingestion points: Reads 'interf.yaml' from the project root.
- Boundary markers: None identified in the prompt instructions.
- Capability inventory: The skill can read local project files and write JSON analysis to the '.interf/previews/' directory. It has no access to the shell or network.
- Sanitization: No input validation or sanitization is specified for the configuration data.
Audit Metadata