icty-ictr-irmct-jeanne-sulzer
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust verification-first methodology that significantly reduces the risk of factual errors and hallucinations in legal research. It explicitly discourages the agent from relying on memory for sensitive legal data.
- [DATA_EXFILTRATION]: The skill uses
web_fetchto retrieve content from well-known, authoritative legal databases (e.g.,irmct.org,icty.org,legal-tools.org). This operation is restricted to the skill's primary research purpose and does not involve the exfiltration of sensitive user information. - [PROMPT_INJECTION]: The skill ingests data from external legal documents, which represents a theoretical attack surface for indirect prompt injection. However, given that these sources are official international records and the skill's workflow involves manual verification and structured citation, the risk is minimal and handled safely.
Audit Metadata