od-video-video-hyperframes
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the $ARGUMENTS variable, which is interpolated into a design brief used by the prepare_open_design_brief tool.
- Ingestion points: The $ARGUMENTS placeholder in SKILL.md.
- Boundary markers: The user-supplied brief is delimited by double quotes.
- Capability inventory: The skill leverages design system recommendation tools, artifact registration tools, and general file-editing capabilities to author design files.
- Sanitization: There is no explicit sanitization or validation of the content provided in the arguments.
Audit Metadata