divination
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill's instructions or reference documentation.\n- [PROMPT_INJECTION]: The skill enforces a rigid structure through its 'Response Contract' and 'Domain Workflows', which explicitly direct the agent to follow fixed analysis sequences rather than arbitrary instructions.\n- [DATA_EXFILTRATION]: All data processing is performed using local MCP tools. There is no evidence of unauthorized network access or transmission of sensitive user data like birth information.\n- [REMOTE_CODE_EXECUTION]: The skill relies on predefined tool handlers within a managed Model Context Protocol environment and does not involve downloading or executing external scripts.
Audit Metadata