use-case-triage
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to read internal documentation at
~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.mdto establish legal context. This is a standard and expected path for this type of organizational plugin. - [SAFE]: No network calls or data exfiltration patterns were detected. The skill process is entirely local to the agent's environment.
- [SAFE]: No remote code execution or package installation commands were found. The skill relies on natural language reasoning and internal logic chains.
- [SAFE]: The instructions contain no prompt injection or bypass attempts. In fact, it includes explicit guardrails (the 'Destination check') to ensure the agent doesn't inadvertently share privileged legal information in public channels or with unauthorized parties.
Audit Metadata