clean-davinci-dialogue
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, word-timed transcripts and dialogue recordings, which could contain hidden instructions that influence the agent's behavior during automated tasks.
- Ingestion points: Processes "word-timed transcripts" and "original dialogue" recordings as referenced in
SKILL.mdandreferences/native-fairlight-chain.md. - Boundary markers: No specific delimiters or explicit instructions to ignore embedded content within the processed data were identified.
- Capability inventory: The skill utilizes the DaVinci Resolve scripting API and MCP for rendering audio, managing timeline positions, and saving project backups.
- Sanitization: No explicit sanitization or validation of transcript content is mentioned in the procedures.
Audit Metadata