china-deal-sourcing
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides templates and workflows for evaluating investment opportunities. No patterns of credential theft, persistence, privilege escalation, or obfuscation were identified.\n- [PROMPT_INJECTION]: The skill involves the ingestion of external data (company filings, market news, and industry data) which presents a surface for Indirect Prompt Injection. However, the operations are limited to data retrieval and reporting, which is standard for this use case and does not involve executing instructions from the data. \n
- Ingestion points: External financial data sources including iFind, AkShare, and stock exchange announcements. \n
- Boundary markers: Absent (Standard data retrieval). \n
- Capability inventory: Limited to financial data queries (e.g., market quotes, financial statements). No dangerous subprocesses or arbitrary code execution capabilities are present. \n
- Sanitization: No explicit sanitization or filtering logic is provided for the retrieved external text.
Audit Metadata