flexport-ci-integration

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external logistics data from the Flexport API, which represents a potential surface for indirect prompt injection if the external data contains instructions intended to influence the agent.\n
  • Ingestion points: API response data is parsed as JSON in the integration test script (tests/integration/flexport.integration.test.ts).\n
  • Boundary markers: Instructions explicitly direct the agent to redact failure references and exclude logistics payloads from final receipts, reducing the risk of accidental instruction leakage.\n
  • Capability inventory: The skill uses Read, Write, Edit, Bash(npm:*), and Grep tools.\n
  • Sanitization: The instructions emphasize excluding credentials, documents, and payloads from output receipts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 08:37 AM
Security Audit — agent-trust-hub — flexport-ci-integration