omni-version-manager
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill facilitates the installation and execution of external services from the npm registry. Specifically, it manages the installation of the '9router', 'cliproxy', 'mux', '@maximhq/bifrost', and '@askalf/dario' packages. While the skill calls a local API to perform these actions, it ultimately triggers the execution of third-party code on the user's machine.
- [EXTERNAL_DOWNLOADS]: The documentation for the 'bifrost' service specifies that the npm package downloads a Go binary from a remote source upon its first execution.
- [COMMAND_EXECUTION]: The skill provides endpoints to configure managed services to start automatically on system boot (e.g., 'POST /api/services/{name}/auto-start'). This establishes a persistence mechanism on the host system via local API commands.
- [PROMPT_INJECTION]: The skill provides an endpoint to stream service logs via Server-Sent Events (SSE). If these services process untrusted data, their logs could contain embedded instructions intended to influence the agent's behavior (indirect prompt injection).
- Ingestion points: Service log buffers accessed via the '/api/services/{name}/logs' endpoint.
- Boundary markers: None identified in the provided documentation.
- Capability inventory: The skill can install/update software, modify service startup configurations, and interact with local account data.
- Sanitization: No evidence of log sanitization or escaping is mentioned in the documentation.
Audit Metadata