browser-qa
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Potential for indirect prompt injection as the skill instructs the agent to process and interact with content from external URLs.
- Ingestion points: Live web pages targeted for QA testing (SKILL.md).
- Boundary markers: Absent; the skill does not define delimiters or warnings to ignore instructions embedded in the analyzed web content.
- Capability inventory: Comprehensive browser automation including navigation, element interaction (clicking, form submission), and screenshotting via MCP tools like claude-in-chrome and Playwright (SKILL.md).
- Sanitization: Absent; the skill does not specify methods for sanitizing web content before processing.
Audit Metadata