composable-functions-skill
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No security issues detected. The skill focuses on scaffolding code structures locally within a project directory.
- Indirect Prompt Injection (LOW): The skill ingests user input (feature names and adapter types) to generate file paths and boilerplate content.
- Ingestion points: User-provided feature name and adapter selection.
- Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: File system write operations for boilerplate generation.
- Sanitization: No explicit sanitization of user-provided strings before file creation is mentioned.
Audit Metadata