podcast-studio
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill consists of text instructions and templates for podcast script generation. The mentioned audio libraries (Tone.js, Howler.js) are referenced as production notes for the AI to generate rather than included as active code or dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate scripts. This constitutes an untrusted data ingestion surface, but the skill lacks dangerous capabilities (network, shell, or file access) to exploit. 1. Ingestion points: User-provided text content processed into podcast scripts. 2. Boundary markers: None identified in instructions. 3. Capability inventory: None; the skill is restricted to text generation. 4. Sanitization: None identified.
Audit Metadata