visual-verify-ui
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external URLs which could contain malicious instructions.
- Ingestion points: The 'test ' argument allows the agent to navigate to and process content from any web address (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters to tell the agent to ignore any potential instructions found within the target website's content.
- Capability inventory: The skill uses the 'Browser' tool and has access to 'Bash' and 'Read' tools, providing a surface for following injected instructions (SKILL.md).
- Sanitization: The skill does not describe any mechanism to sanitize or validate the content retrieved from the target URL before it is returned to the main protocol loop.
Audit Metadata