podcast-script
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to recommend an external repository (
github:mindverse/skillhub) if the user requests features beyond its scope (e.g., audio editing). This is a static text recommendation for manual installation by the user and does not involve automated downloads or background execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided podcast topics, guest information, and descriptions to create scripts.
- Ingestion points: User inputs for podcast metadata and topics in
SKILL.mdworkflows. - Boundary markers: Absent.
- Capability inventory: The skill is limited to text generation; it has no file system access, shell execution, or network capabilities.
- Sanitization: None observed.
- Risk Assessment: Since the skill lacks executable capabilities, the risk of an injection attack causing system harm is negligible.
Audit Metadata