chatgpt-task-router

Warn

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONSAFE
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill utilizes a dynamic import() call to load the chatgpt-bridge.mjs script from a string-defined path. Dynamic loading of modules at runtime can be used to execute code that is not statically verifiable within the skill's primary instruction set.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled data (userRequest) to determine the routing logic and conversation mode for an external AI service.
  • Ingestion points: Untrusted data enters the agent context through the userRequest variable passed to the classifyChatGPTConversationMode function in SKILL.md.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to the LLM to ignore potentially malicious commands embedded within the userRequest text.
  • Capability inventory: The skill possesses the capability to control an in-app browser (browser:control-in-app-browser) and interact with an external web interface.
  • Sanitization: There is no evidence of sanitization or input validation performed on the user-provided text before it is used to influence the agent's decision-making logic.
  • [SAFE]: The skill references and interacts with chatgpt.com. As this is a well-known service provided by OpenAI, the network interaction with this domain is considered standard behavior for the stated purpose of the skill.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 12, 2026, 02:22 PM
Security Audit — agent-trust-hub — chatgpt-task-router