figma-agent-brief
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from intent documents and audit files to structure design briefs.
- Ingestion points: Reads content from files specified via the
--intentand--readiness-scorearguments in SKILL.md. - Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore embedded commands within the input files.
- Capability inventory: The skill's primary function is text generation and structuring; it does not perform network operations, subprocess calls, or sensitive file system modifications.
- Sanitization: Implements 'Quality gates' to validate that the output follows a specific hierarchical structure and excludes narrative prose, which serves as a structural filter for the generated content.
Audit Metadata