module-pattern
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a pattern where dynamic
import()calls use expressions influenced by untrusted data sources. - Ingestion points: The 'Dynamic import' section explicitly mentions loading modules based on 'user input' or 'data received from an external source' using template literals.
- Boundary markers: The skill does not provide any instructions on using delimiters or boundary markers to isolate untrusted input.
- Capability inventory: The skill encourages the agent/developer to use dynamic loading capabilities for flexibility.
- Sanitization: There is no mention of validating, escaping, or sanitizing the input before it is interpolated into the dynamic import expression.
- [DYNAMIC_EXECUTION]: The instructions promote dynamic loading from computed paths. Specifically, the use of template literals within the
import()function allows for the execution/loading of code or assets determined at runtime. While this is a standard JavaScript feature, recommending its use with external or user-provided data without validation is a security risk factor that facilitates the loading of arbitrary resources.
Audit Metadata