cli-eval
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the
omnirouteCLI tool, which is managed via standard package managers (npm install -g omniroute). It also references documentation and configuration files hosted on the author's project repository on GitHub. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data provided in JSONL format via the
--samples-fileflag. - Ingestion points: The
omniroute eval suites createcommand reads test samples from local file paths specified by the user. - Boundary markers: The skill does not explicitly define specific boundary markers for the ingested sample content.
- Capability inventory: The skill performs file reading and executes shell commands through the CLI tool to process evaluations.
- Sanitization: There is no mention of sanitization for the input data, as the tool is designed to process arbitrary prompt/output pairs for evaluation purposes.
Audit Metadata