skills/ruvnet/ruflo/iot-fleet/Gen Agent Trust Hub

iot-fleet

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the @claude-flow/plugin-iot-cognitum package from the NPM registry at runtime.\n- [COMMAND_EXECUTION]: Core functionality is implemented through shell commands executed via the npx utility.\n- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for command injection.\n
  • Ingestion points: User-provided NAME, FLEET_ID, and DEVICE_ID arguments within the SKILL.md commands.\n
  • Boundary markers: No delimiters or protective instructions are used to isolate user input from the shell command structure.\n
  • Capability inventory: The skill has the ability to execute arbitrary shell commands via the Bash tool and npx.\n
  • Sanitization: There is no evidence of input validation, escaping, or filtering for shell metacharacters in the user-supplied arguments before they are executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:38 AM
Security Audit — agent-trust-hub — iot-fleet