browser-qa
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by directing the agent to interact with and extract information from external web pages, creating a vulnerability surface where malicious instructions could be ingested from the target sites.
- Ingestion points: Data enters the agent context through page navigation, reading HTML content, monitoring console logs, and evaluating network responses as described in
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when the agent parses text or data from the audited websites.
- Capability inventory: The skill leverages network capabilities for browser navigation and interaction (clicks, form submission) and file system access for storing screenshots.
- Sanitization: There is no evidence of sanitization or filtering logic applied to the text content retrieved from external sites before it is processed by the agent.
Audit Metadata