Faceless Video
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied 'topic' and 'source material' to draft scripts and generate media assets, creating an indirect prompt injection surface.
- Ingestion points: Untrusted data enters the agent context through the 'topic' and 'source material' inputs specified in the 'Required inputs' section.
- Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to ignore embedded instructions within the ingested data.
- Capability inventory: The skill utilizes powerful generative tools including
media.generate_video,media.generate_image,media.generate_speech, andmedia.combine_video. - Sanitization: Absent; there are no explicit steps for sanitizing or validating user-provided content before it is used for script generation and asset production.
Audit Metadata