ui-visual-validator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external visual evidence such as screenshots, which serves as a potential surface for indirect prompt injection if malicious instructions are embedded within the images. * Ingestion points: The agent is instructed to perform 'Screenshot analysis with pixel-perfect precision' and 'Visual diff detection' (documented in SKILL.md). * Boundary markers: The skill does not provide specific delimiters or instructions to ignore or isolate text found within screenshots from the agent's core instructions. * Capability inventory: The skill consists of markdown-based instructions and does not incorporate executable scripts, subprocess calls, or network-enabled tools. * Sanitization: There is no defined logic for sanitizing or validating content extracted from processed visual evidence.
Audit Metadata