generate-educational-music-video
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the
lyrics.mdfile. While this represents a surface for indirect prompt injection, the structured nature of the processing pipeline (translation, segmentation, mood extraction) mitigates the risk of the agent executing hidden commands. - Ingestion points:
lyrics.mdis the primary input source. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the lyrics.
- Capability inventory: The skill performs file system writes and calls external visual generation tools.
- Sanitization: No specific sanitization or filtering of the input lyrics is described.
- [EXTERNAL_DOWNLOADS]: The skill makes calls to the Replicate service for image and video generation. As a well-known AI infrastructure service, its use for the skill's core purpose of visual generation is considered safe and functional.
Audit Metadata