visual-qa-testing
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is instructional and facilitates testing of local development environments. It uses documented browser tools to perform UI audits.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from web pages (console logs, network requests). However, the risk is considered safe as the primary intended target is the developer's local environment. 1. Ingestion points: Data enters the agent context through 'browser_console_messages' and 'browser_network_requests' in SKILL.md. 2. Boundary markers: No specific delimiters are defined to separate tool output from instructions. 3. Capability inventory: The skill utilizes subprocess execution ('npm run dev') and browser interaction tools. 4. Sanitization: No explicit sanitization is performed on the content retrieved from the web application.
Audit Metadata