site-launch-checklist
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Figma files (such as layer names, text content, and comments) that could contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: Accesses Figma frames, components, instances, variables, styles, layers, prototype settings, comments, sections, and annotations (defined in SKILL.md).\n
- Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions to separate untrusted data from the agent's system instructions.\n
- Capability inventory: The skill can perform scoped, reversible edits to the Figma file when the user requests fixes.\n
- Sanitization: No explicit sanitization or validation logic is defined for the content extracted from the design file.
Audit Metadata