legal-request-router-pl
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts exclusively as a decision-making layer for legal workflows. It contains no malicious patterns, prompt injections, or obfuscated content.
- [DATA_EXFILTRATION]: The skill is configured for local data residency and prohibits PII egress. There are no network-capable tools or patterns for exfiltrating data to external domains.
- [REMOTE_CODE_EXECUTION]: No external dependencies, package installations, or remote script execution patterns are present. The skill relies entirely on natural language instructions and local metadata.
- [COMMAND_EXECUTION]: The skill only permits the
Readtool, and there is no evidence of shell commands, subprocess spawning, or persistence mechanisms. - [PROMPT_INJECTION]: The instructions are focused on structured output for routing decisions and do not contain any bypass attempts, DAN-style injections, or instructions to ignore safety protocols.
Audit Metadata