bse-selection-analyzer
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill refers to the use of an authentication token (
XUEQIU_TOKEN) for certain data requests. It correctly recommends setting this as an environment variable rather than hardcoding credentials. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external financial APIs (EastMoney, AKShare) through local scripts. While this creates an injection surface, the risk is minimal as the data is structured financial information from trusted providers.
- Ingestion points: Financial data views described in
references/data-queries.md. - Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: The skill is intended to execute local Python scripts for data retrieval.
- Sanitization: Not explicitly mentioned, though data is expected in structured JSON format.
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill provides instructions to install dependencies and run scripts from a local sibling directory (
../findata-toolkit-cn/). These actions are standard for the tool's documented purpose and target local resources rather than untrusted remote sources.
Audit Metadata