ai-podcast-creation
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and suggests installing external tools and documentation from the inference-sh GitHub organization and via npx.
- Evidence: Mentions npx skills add belt-sh/cli and links to installation guidelines on GitHub.
- [INDIRECT_PROMPT_INJECTION]: The skill processes document content by interpolating it into LLM prompts for script generation, which presents a surface for indirect prompt injection.
- Ingestion points: The placeholder in SKILL.md.
- Boundary markers: None; the untrusted content is directly embedded in the prompt payload.
- Capability inventory: Execution of belt commands via the Bash tool.
- Sanitization: No content sanitization or validation logic is defined.
Audit Metadata