node-connect

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses the openclaw CLI tool to perform diagnostic read operations and manage device pairings within the scope of its defined purpose.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from user-provided error messages to guide diagnostic decisions and administrative actions such as device pairing approval. This represents an indirect prompt injection surface.\n
  • Ingestion points: User-provided error logs and app status text requested during the troubleshooting flow.\n
  • Boundary markers: The skill instructs the agent to ask for quoted text but lacks structured delimiters for processing this input internally.\n
  • Capability inventory: The skill utilizes CLI commands that can approve device pairings (openclaw devices approve) and read system configuration.\n
  • Sanitization: No explicit sanitization or validation of the ingested user text is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:22 AM
Security Audit — agent-trust-hub — node-connect