qa-testcase-from-ui
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied images (screenshots, Figma exports, wireframes) which may contain malicious text instructions designed to manipulate the agent's output.
- Ingestion points: Image file paths (PNG, JPG, WebP, SVG, PDF) analyzed via vision capabilities as specified in
SKILL.md. - Boundary markers: No explicit instructions or delimiters are used to separate the extracted UI text from the agent's core instructions.
- Capability inventory: The skill is limited to vision analysis and markdown file generation in the
test-cases/from-uidirectory. No network or shell tools are utilized. - Sanitization: No sanitization or filtering of text recognized via OCR/vision is mentioned in the workflow.
Audit Metadata