visual-validate
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from browser interactions, console logs, and network metadata.
- Ingestion points: Data enters the agent context through browser navigation and logging tools in SKILL.md.
- Boundary markers: No delimiters or ignore instructions are present to protect the agent from embedded commands in web content.
- Capability inventory: The skill can execute browser interactions (clicks, keyboard input) and write screenshot files.
- Sanitization: External content from the browser is not sanitized or filtered before analysis.
Audit Metadata