trial-contract-terms
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content such as contract memos and drafts which could contain hidden instructions designed to influence the agent's analysis.
- Ingestion points: User-provided text for contract analysis, plans, and drafts in
SKILL.md(Steps 1, 3). - Boundary markers: Absent. Instructions specify copying text verbatim from the source documents.
- Capability inventory: Execution of bundled Python script
check_contract_terms.py. - Sanitization: Absent. No explicit filtering or escaping of the ingested text is performed before processing or interpolation into reports.
- [EXTERNAL_DOWNLOADS]: Fetches regulatory information and guidelines from the Japanese Ministry of Health, Labour and Welfare's official website.
- [EXTERNAL_DOWNLOADS]: References contract terms and service information from the vendor's official domains (
otame4.work,employer.otame4.work).
Audit Metadata