cli-models
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends global installation of the omniroute CLI tool from npm (npm install -g omniroute). While central to the skill's functionality, it introduces an external dependency that is not pinned to a specific version.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to query and display metadata from external AI model providers, creating a potential vector for indirect prompt injection if a provider returns malicious content.
- Ingestion points: CLI output from omniroute models commands in SKILL.md.
- Boundary markers: No delimiters or safety warnings are provided for handling external model metadata.
- Capability inventory: The skill uses shell execution to interact with the system and remote APIs via the CLI tool.
- Sanitization: No explicit sanitization or validation of the fetched model metadata is mentioned.
Audit Metadata