kelly-legal-matter-strategy
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted case data (facts, evidence) to generate legal strategy packs, creating an indirect prompt injection surface. Mitigation includes specific agent instructions for data grounding and HTML escaping in the UI code to prevent malicious content from influencing the agent or user.\n- [EXTERNAL_DOWNLOADS]: The skill incorporates the
busabase-sdkand Hono server libraries, which are standard, well-maintained packages retrieved from the official npm registry.\n- [COMMAND_EXECUTION]: Local Node.js scripts are provided for case data ingestion and approved strategy export. These operations are limited to the user's local filesystem and the authorized Busabase API, consistent with the skill's stated purpose.
Audit Metadata