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

iot-anomalies

Warn

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the @claude-flow/plugin-iot-cognitum package from the NPM registry at runtime using the npx utility.
  • [REMOTE_CODE_EXECUTION]: Executes remote code via npx -y -p. The use of the @latest version identifier means the skill will always run the most recent version of the package, creating a potential vector for supply chain attacks if the package or its registry entry is compromised.
  • [COMMAND_EXECUTION]: Spawns a bash shell to execute the npx command and the cognitum-iot CLI tool.
  • [PROMPT_INJECTION]: Contains a surface for indirect prompt injection via the processing of IoT telemetry data.
  • Ingestion points: Telemetry data fetched by the cognitum-iot command-line tool.
  • Boundary markers: Absent. The skill does not provide delimiters or instructions to treat the data as untrusted, increasing the risk that instructions embedded in telemetry could be executed by the agent.
  • Capability inventory: Shell execution (npx), file reading (Read), and memory storage (mcp__claude-flow__memory_store).
  • Sanitization: Absent. The agent directly interprets anomaly types and scores from the tool's output to perform actions such as device quarantine.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 17, 2026, 06:09 PM
Security Audit — agent-trust-hub — iot-anomalies