frame-light-leak-cinema
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a legitimate workflow for a design assistant to generate cinematic video frames. It uses a specific set of tools (Open Design MCP server) for their intended purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to generate design briefs, creating a potential surface for indirect instructions.
- Ingestion points: User messages are treated as the brief in
SKILL.md. - Boundary markers: The skill instructs the agent to treat the user's message as the brief but does not define explicit delimiters for the input.
- Capability inventory: The skill utilizes file-editing tools and artifact registration tools referenced in
SKILL.md. - Sanitization: No explicit sanitization or input validation is defined for the user-provided brief.
- Note: This is a standard functional surface for a design-oriented skill and does not represent an active malicious pattern.
Audit Metadata