mediation-dispute-analysis
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within its documented scope of providing mediation and dispute analysis. It uses provided assets (templates and reference guides) to assist the user in legal preparation without executing dangerous commands.
- [PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection as it is designed to ingest and summarize untrusted external data (pleadings, contracts, correspondence).
- Ingestion points:
SKILL.mdidentifies file uploads and pasted text (Step 2 and Mode B) as sources of case data. - Boundary markers: The skill lacks explicit boundary markers or 'ignore instructions' delimiters for user-provided data.
- Capability inventory: The skill can generate text in chat and create
.docxfiles via a specialized tool. It does not possess capabilities for arbitrary shell execution, system-level file access (beyond its own assets), or network operations. - Sanitization: No explicit sanitization or filtering of input data is defined in the instructions.
Audit Metadata