cli-resilience

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the omniroute package globally using npm or execute it via npx.
  • [COMMAND_EXECUTION]: The skill invokes the omniroute command-line utility with various subcommands and flags to inspect and modify system states.
  • [INDIRECT_PROMPT_INJECTION]: The quota ensure <json> command accepts structured JSON data as input. This creates a potential surface for indirect prompt injection if the data processed by the tool or subsequent agent steps contains instructions that attempt to influence the agent's behavior.
  • Ingestion points: The <json> argument in the quota ensure subcommand.
  • Boundary markers: None provided in the skill instructions to delimit the data from instructions.
  • Capability inventory: Execution of shell commands via the omniroute CLI.
  • Sanitization: No explicit sanitization or validation logic is defined for the input data in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 04:29 AM