webull-openapi
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
webull-openapi-python-sdkfrom an external repository (github.com/webull-inc/webull-openapi-python-sdk). This dependency is necessary for the skill's primary function of interacting with the Webull API.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, including writing JSON order data to local temporary files (e.g.,/tmp/order.json) and running thewebull-skillCLI (SKILL.md).\n- [INDIRECT_PROMPT_INJECTION]:\n - Ingestion points: The skill ingests untrusted data from external sources via market data actions such as
stock-snapshot,stock-bars, andstock-tick, which fetch real-time information from Webull's API (SKILL.md, references/skill_market_data.md).\n - Boundary markers: The instructions lack explicit boundary markers or delimiters to separate ingested market data from agent instructions.\n
- Capability inventory: The skill possesses significant capabilities, including the ability to place, replace, and cancel financial orders for stocks, options, futures, and crypto via the
webull-skillCLI (SKILL.md, references/skill_trading.md).\n - Sanitization: No specific methods for sanitizing or validating the content of the API responses are described, creating a potential surface for indirect prompt injection if the API data is manipulated.
Audit Metadata