special-panels-timor-leste-jeanne-sulzer
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on research methodology and citation standards for international criminal tribunals. No evidence of credential theft, persistence, privilege escalation, or code obfuscation was found within the instructions or reference materials.
- [EXTERNAL_DOWNLOADS]: The skill workflow involves retrieving data from external legal and historical archives including 'jsmp.tl', 'etan.org', 'cavr-timorleste.org', and 'legal-tools.org'. These are specialized, reputable repositories for documents related to Timor-Leste's judicial history and international law.
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface as it processes external data from the web.
- Ingestion points: Data enters the agent's context through the 'web_fetch' operation on external sites listed in 'references/authoritative-sources.md'.
- Boundary markers: None. The instructions do not provide explicit delimiters or instructions to treat fetched content as untrusted data.
- Capability inventory: The agent is directed to fetch web content; no direct file system access or subprocess execution capabilities are granted by this skill.
- Sanitization: None. There are no instructions for validating or sanitizing the content retrieved from external sources.
Audit Metadata