navan-incident-runbook

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents standard operational procedures for incident response related to the Navan travel platform, including booking failures and API outages.
  • [COMMAND_EXECUTION]: Includes Bash scripts for testing API health and OAuth authentication. These scripts use standard tools (curl, jq) and target legitimate Navan endpoints (api.navan.com).
  • [CREDENTIALS_UNSAFE]: The skill correctly handles sensitive data by instructing the user to store credentials in a secret manager and accessing them via environment variables ($NAVAN_CLIENT_ID, $NAVAN_CLIENT_SECRET) rather than hardcoding them.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data exfiltration. Network requests are limited to official Navan domains for the purpose of service status verification and authentication.
  • [PROMPT_INJECTION]: No malicious injection patterns or instruction overrides were detected in the skill instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 12:36 PM
Security Audit — agent-trust-hub — navan-incident-runbook