design-handoff
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of Figma URLs and design descriptions to generate documentation. If an attacker-controlled design or description contains hidden instructions, the agent might inadvertently follow them during the generation process.
- Ingestion points: Design data and metadata retrieved from Figma URLs or design descriptions provided in the
$ARGUMENTSparameter (SKILL.md). - Boundary markers: Absent. There are no explicit delimiters or instructions to ignore potential commands embedded within the design data.
- Capability inventory: The skill generates markdown documentation and can potentially interact with a project tracker to link tickets or create sub-tasks.
- Sanitization: Absent. There is no evidence of input validation or content filtering for the design data.
Audit Metadata