pilot-customer-support-triage-setup

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The analysis of the instructions and configuration manifests identified no malicious code or security threats.
  • [COMMAND_EXECUTION]: The setup procedure involves routine administrative commands using clawhub and pilotctl for system configuration and component management within the Pilot Protocol framework.
  • [EXTERNAL_DOWNLOADS]: The skill downloads functional agent capabilities from the official clawhub registry, which is the expected source for this framework's components.
  • [PROMPT_INJECTION]: The system architecture handles external customer ticket data, creating a surface for indirect prompt injection. Ingestion points: Ticket data is published via pilotctl JSON events. Boundary markers: Data is structured in JSON format. Capability inventory: The system includes webhook and Slack integration tools for escalation. Sanitization: No explicit content filtering or sanitization logic is defined in the provided setup manifests.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 03:16 AM
Security Audit — agent-trust-hub — pilot-customer-support-triage-setup