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-sdk from 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 the webull-skill CLI (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, and stock-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-skill CLI (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
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:56 PM
Security Audit — agent-trust-hub — webull-openapi