creating-podcast-show-notes
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted transcript or audio data to generate summaries, social media posts, and show notes. This creates an attack surface where instructions embedded in the podcast content could be interpreted as commands by the AI.
- Ingestion points: Transcripts and audio files processed in
SKILL.md(Step 2). - Boundary markers: The instructions lack specific delimiters or instructions to ignore commands found within the source material.
- Capability inventory: No dangerous system capabilities such as command execution, file system writes, or network exfiltration were identified in the provided files.
- Sanitization: The instructions do not include steps to sanitize or validate the content of the transcript before processing.
Audit Metadata