fx
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- NO_CODE (SAFE): The skill file consists entirely of documentation and instructions in Markdown format. There are no executable code blocks, shell commands, or script files provided within the skill package.
- INDIRECT_PROMPT_INJECTION (INFO): The skill instructs the agent to retrieve data from external financial websites. Ingestion points: pbc.gov.cn, cfets.org.cn, and boc.cn. Boundary markers: None specified. Capability inventory: None (display only). Sanitization: No technical sanitization of external content is defined. While this exposes the agent to untrusted external data, the risk is limited to misinformation as the skill lacks write, execute, or exfiltration capabilities.
Audit Metadata