cli-batches

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation instructs the user to install the omniroute CLI globally via npm install -g omniroute or run it via npx.
  • [COMMAND_EXECUTION]: The skill relies on executing various omniroute shell commands to manage batches and files.
  • [DATA_EXFILTRATION]: The files upload <path> command enables the agent to read local files and transmit them to the external batch processing service.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface when reading untrusted data from external sources.
  • Ingestion points: Data enters the agent's context through omniroute batches output and omniroute files content commands.
  • Boundary markers: No specific delimiters or safety warnings are implemented to differentiate between data and instructions when processing these outputs.
  • Capability inventory: The agent has the ability to execute shell commands (via the omniroute CLI) and perform file system operations (upload/download).
  • Sanitization: There is no evidence of validation or sanitization of the content retrieved from batch jobs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 01:50 AM
Security Audit — agent-trust-hub — cli-batches