tushare
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to the Tushare API at
tushare.proto retrieve financial datasets. These operations are restricted to the vendor's own infrastructure and are necessary for the skill's primary function. - [COMMAND_EXECUTION]: The skill includes Python scripts (
scripts/fund_data_demo.pyandscripts/stock_data_demo.py) used to automate data retrieval and processing. These scripts use the officialtusharelibrary to interact with the API. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from API responses.
- Ingestion points: Data is ingested from various Tushare API endpoints such as
daily,fund_nav, andfina_indicator(identified inSKILL.mdandscripts/). - Boundary markers: No explicit boundary markers or instructions to ignore embedded content are present in the scripts.
- Capability inventory: The skill possesses network access to the vendor's API, the ability to execute Python code, and the capability to write data to the local file system (CSV/Parquet exports).
- Sanitization: Data is handled as structured objects using the
pandasandtusharelibraries, which mitigates many common injection risks compared to raw text processing.
Audit Metadata