game-ux-designer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is instructed to process data from external, potentially untrusted sources.
- Ingestion points: As described in the 'MCP Integration' section of
SKILL.md, the agent pulls UI designs from Figma files and interacts with web game builds using Playwright to extract content, metadata, and accessibility roles. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested Figma files or web page content are present.
- Capability inventory: The skill is configured with
WriteandEdittools in the frontmatter, and the instructions task the agent with writing detailed specifications and audit reports based on the ingested data. - Sanitization: There are no explicit sanitization steps mentioned for processing the external input before it is used to generate documentation or specifications.
Audit Metadata