podcast-and-audiograms
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of podcast recordings and transcripts provided in the episode context. Ingestion points: the episode (recording + transcript) as defined in SKILL.md and references/scope-and-connections.md. Boundary markers: None explicitly implemented to delimit untrusted transcript data from instructions. Capability inventory: The agent generates hooks, CTAs, and marketing plans. It does not possess direct file-write or system-level execution capabilities. Sanitization: No explicit sanitization or filtering of transcript content is performed. The skill relies on human review as the final step in the pipeline.
- [EXTERNAL_DOWNLOADS]: The skill documentation and reference files (e.g., references/podcast-to-social-2026-reality.md) mention and recommend various third-party SaaS tools and platforms including Opus Clip, Headliner, WoopSocial, and Descript. These are well-known industry services for media repurposing and social media management.
Audit Metadata