new-designation-screening-test

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external regulatory websites (ofac.treasury.gov, gov.uk, europa.eu), which creates an indirect prompt injection surface. This is a standard risk for skills designed to ingest and process dynamic web content. Ingestion points: Regulatory update pages and notices specified in Step 1 of the SKILL.md workflow. Boundary markers: Not utilized in the instructions. Capability inventory: Data extraction and file generation via the xlsx tool. Sanitization: No specific filtering or validation of the retrieved web content is defined.
  • [EXTERNAL_DOWNLOADS]: The skill references and retrieves data from official government domains and well-known regulatory services. These external connections are essential to the skill's purpose and target trusted official sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 08:34 PM
Security Audit — agent-trust-hub — new-designation-screening-test