code-engine
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes patterns for ingesting untrusted data (function parameters) and transmitting them via
domo.postto a remote execution environment (Domo Code Engine). - Ingestion points: The
payloadobject in theexecuteFunctionandparamsindomo.postcalls withinSKILL.mdare used to pass data to remote functions. - Boundary markers: The provided templates do not specify delimiters or instructions to prevent embedded instructions in the payload from being executed by the remote Code Engine function.
- Capability inventory: The skill utilizes
domo.postfor network operations and references package execution. - Sanitization: The instruction set focuses on response normalization (unwrapping envelopes) but does not include patterns for sanitizing or validating input data before it is sent to the external service.
- [EXTERNAL_DOWNLOADS]: The skill references the installation of
ryuu.jsvianpm. This is the standard development SDK for the Domo platform and is considered a well-known service.
Audit Metadata