iot-firmware

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download the @claude-flow/plugin-iot-cognitum package from the npm registry at runtime.
  • [COMMAND_EXECUTION]: Executes shell commands via npx to perform firmware deployment, advancement, and rollback operations across device fleets.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through the interpolation of user-provided data into shell commands.
  • Ingestion points: Arguments such as FLEET_ID, VERSION, and ROLLOUT_ID are provided by the user and used directly in command execution.
  • Boundary markers: There are no boundary markers or instructions to isolate user input from the command syntax.
  • Capability inventory: The skill utilizes the Bash tool (via npx) to execute system-level commands.
  • Sanitization: No sanitization or validation logic is defined within the skill instructions to process external inputs before they are used in the shell environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:23 PM
Security Audit — agent-trust-hub — iot-firmware