editor-motion-graphics
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from video transcripts and project timelines to determine where and what graphics to generate.
- Ingestion points: Data is ingested via
footage_getTranscriptandtimeline_describe. - Boundary markers: No specific delimiters or boundary instructions are provided to help the agent distinguish between transcript text and its own instructions.
- Capability inventory: The skill utilizes tools including
media_generate,timeline.moveClip,timeline.setClipDuration, andtimeline_deleteClips. - Sanitization: No sanitization or validation of the transcript content is specified before it is used as the basis for graphic generation prompts.
Audit Metadata