podcaster-pro
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external transcripts to generate summaries, timestamps, and promotional content, which introduces a surface for indirect prompt injection.
- Ingestion points: The skill reads user-provided transcripts and outlines to generate show notes and teaser clips (defined in
SKILL.mdunder Step 4 and 5). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the ingested transcript data.
- Capability inventory: The skill primarily performs text transformation and instructs the agent to save output as Markdown files; it lacks network access, shell execution, or privilege escalation capabilities.
- Sanitization: There is no evidence of input filtering or sanitization for the transcript content before it is processed by the agent.
Audit Metadata