ksc-jeanne-sulzer

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to retrieve legal documents and case information from official institutional domains, including scp-ks.org (the official Kosovo Specialist Chambers website) and legal-tools.org (the ICC Legal Tools Database). These sources are recognized as official repositories for international justice records.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting external data from tribunal websites, creating a potential attack surface for indirect prompt injection.
  • Ingestion points: Instructions in SKILL.md and references/verification-workflow.md direct the agent to fetch case filings and judgments using web retrieval tools.
  • Boundary markers: The skill implements a 'verification ladder' (Existence, Content, and Paragraph levels) to ensure data accuracy and provides explicit warnings against using unverified appeal registry numbers.
  • Capability inventory: The skill consists of instructional markdown files and does not include any scripts, binary executables, or autonomous command-execution capabilities.
  • Sanitization: No specific text sanitization or escaping mechanisms for the fetched content are described, though the multi-level verification process acts as a manual oversight mechanism.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:33 PM
Security Audit — agent-trust-hub — ksc-jeanne-sulzer