browser-qa
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns such as direct prompt injection, data exfiltration, or unauthorized command execution were found. The skill instructions focus entirely on legitimate UI and accessibility testing workflows.
- [NO_CODE]: This skill consists solely of instructions and does not include executable scripts or external code dependencies, which minimizes its direct security footprint.
- [PROMPT_INJECTION]: The skill interacts with external websites, creating a surface for indirect prompt injection. Ingestion points: Target URLs accessed during QA phases (SKILL.md). Boundary markers: Absent from the provided instructions. Capability inventory: Browser automation tools for navigation, element interaction, and data retrieval (SKILL.md). Sanitization: No validation or filtering of external site content is specified.
Audit Metadata