qa-engineer
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill incorporates user-provided data via the $ARGUMENTS placeholder. This creates a potential surface for indirect prompt injection because the agent processes external input without explicit delimiters or sanitization.
- Ingestion points: $ARGUMENTS in SKILL.md.
- Boundary markers: Not present.
- Capability inventory: Automated browser interactions and quality audits via Chrome DevTools.
- Sanitization: Not present.
Audit Metadata