skills/ruvnet/claude-flow/iot-fleet/Gen Agent Trust Hub

iot-fleet

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes the @claude-flow/plugin-iot-cognitum package from the NPM registry using the npx utility at runtime.
  • [COMMAND_EXECUTION]: Functions by executing shell commands to interact with the Cognitum IoT fleet management service.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (specifically command injection) because it interpolates user-supplied arguments directly into bash execution strings.
  • Ingestion points: Subcommand arguments such as NAME, FLEET_ID, and DEVICE_ID defined in SKILL.md.
  • Boundary markers: No delimiters or warning instructions are present to separate user input from the command structure.
  • Capability inventory: Employs the Bash tool to execute all operations, including those incorporating user input.
  • Sanitization: The skill does not specify any sanitization, escaping, or validation logic for the input arguments before they are passed to the shell environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:23 PM
Security Audit — agent-trust-hub — iot-fleet