code-engine-create
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
community-domo-clitool to perform package creation and lifecycle operations in a CLI environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that processes untrusted data to create executable packages, creating a vulnerability surface.\n - Ingestion points: The skill ingests user-supplied JavaScript source code and package metadata (name and description) to populate the
manifest.functionsandcodefields of the payload.\n - Boundary markers: There are no explicit delimiters or instructions to the agent to isolate or ignore embedded commands within the user-provided code or metadata.\n
- Capability inventory: The skill possesses the capability to execute CLI commands, perform network operations (HTTP POST and GET), and modify local project configuration files (
manifest.json).\n - Sanitization: No sanitization, escaping, or validation logic is defined for the user-provided content before it is included in the package creation payload.
Audit Metadata