icc-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 use web retrieval tools to fetch documents from official International Criminal Court domains (icc-cpi.int, asp.icc-cpi.int) and established legal databases (legal-tools.org, opil.ouplaw.com). These are authoritative sources used for citation verification and research.
  • [COMMAND_EXECUTION]: The skill utilizes platform-provided web search and fetch tools to interact with the aforementioned official legal resources. This is the core mechanism for its 'verification-first' methodology, ensuring that legal citations are matched against primary sources before being presented to the user.
  • [DATA_EXPOSURE]: No sensitive local file paths or environment variables are accessed. The skill focuses exclusively on public Court records and foundational legal instruments.
  • [PROMPT_INJECTION]: There are no patterns suggesting attempts to bypass AI safety guardrails. Instead, the instructions provide a structured, disciplined workflow that reinforces accuracy and prevents the fabrication of information.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:32 PM
Security Audit — agent-trust-hub — icc-jeanne-sulzer