verify-site
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from external or local websites during the verification process, creating a surface for indirect prompt injection.\n
- Ingestion points: Website content and console logs are ingested via
browser_navigate,browser_snapshot, andbrowser_console_messagesas described inSKILL.md.\n - Boundary markers: The instructions do not include specific delimiters or warnings to ignore embedded instructions within the processed website data.\n
- Capability inventory: The agent uses tools for browser interaction (
browser_click,browser_fill_form,browser_evaluate) and is explicitly instructed to fix bugs in the code using file-writing capabilities.\n - Sanitization: No sanitization or validation of the ingested web content is performed before processing.
Audit Metadata