vibe-coding-ui-review
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of user-provided screenshots and local project files (
./docs/DESIGN_SYSTEM.mdandTECH_STACK.md). This creates a potential surface for indirect prompt injection if the screenshots contain adversarial text instructions. - Ingestion points: User-provided UI screenshots and local markdown documentation files.
- Boundary markers: Absent. The skill does not instruct the agent to ignore or delimit instructions that might be embedded within the text of the screenshots.
- Capability inventory: The skill is restricted to generating text-based reports and code snippets for UI fixes; it does not explicitly request file system write access, network operations, or shell execution.
- Sanitization: No explicit sanitization or validation of the content extracted from images or documentation is defined.
Audit Metadata