video-hyperframes
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate a design brief, which is then used to guide the agent's file-authoring actions. This creates a surface where instructions embedded in user data could potentially influence agent behavior during the design process.
- Ingestion points: The user's message is treated as the brief in
SKILL.md. - Boundary markers: The skill does not provide explicit delimiters or instructions to the agent to treat the brief content as untrusted data.
- Capability inventory: The agent is instructed to use file-editing tools to author files based on returned instructions and call
register_open_design_artifact. - Sanitization: There is no mention of sanitization, validation, or filtering of the user-provided brief content.
Audit Metadata