notte
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill facilitates the extraction of sensitive browser data including session cookies and network logs through dedicated endpoints such as
/sessions/{session_id}/cookies.\n- [COMMAND_EXECUTION]: The skill allows execution of arbitrary actions within a browser environment, such as typing, clicking, and navigating, which are core to its automation functionality.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface:\n - Ingestion points: Untrusted data enters the context via web scraping and page observation endpoints (
/scrape,/sessions/{session_id}/page/observe).\n - Boundary markers: No delimiters or instructions to ignore embedded instructions are present to protect the agent from malicious web content.\n
- Capability inventory: The skill provides significant capabilities, including executing page actions, modifying cookies, and starting autonomous agents.\n
- Sanitization: No explicit sanitization or validation of external content is described before it is processed by the agent.
Audit Metadata