lyric-video
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill workflow is designed to ingest and process external data that could potentially contain malicious instructions.\n
- Ingestion points: The workflow in
SKILL.mdrequires the agent to use an "approved lyric source" and "final audio" provided at runtime.\n - Boundary markers: The instructions lack specific delimiters or directives to prevent the agent from following instructions embedded within the lyric text.\n
- Capability inventory: The skill involves the creation of "final export" assets, which implies the use of file-writing or media-processing tools by the agent.\n
- Sanitization: No sanitization or validation logic is defined to check the integrity of the external lyric source before it is treated as canonical.\n- [EXTERNAL_DOWNLOADS]: The skill references external media and portfolio websites for production research.\n
- Evidence: The
references/lyric-video.mdfile contains links to well-known media platforms such as YouTube, Vimeo, and Behance, as well as artist and studio websites likemrsgreenapple.comandstudiosparks.com. These are provided for comparative analysis and observation purposes.
Audit Metadata