ui-design-to-image
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to resolve paths for and execute external scripts (scripts/main.ts) with arguments derived from potentially untrusted design briefs.\n- [DYNAMIC_EXECUTION]: The agent is tasked with dynamically determining runtimes and skill directories at execution time to run backend scripts.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted design briefs that are subsequently incorporated into image generation prompts, creating a potential surface for indirect prompt injection.\n
- Ingestion points:
SKILL.md,references/image-contract.md(briefs, page/task contracts).\n - Boundary markers: Absent; prompt templates do not define strict delimiters for external content.\n
- Capability inventory:
references/backends.md(Subprocess execution ofscripts/main.ts).\n - Sanitization: Absent; instructions recommend quoting verbatim labels but do not mandate escaping or validation.
Audit Metadata