kong-gateway

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to execute administrative commands against a Kong Gateway API via the configurable KONG_ADMIN_URL environment variable.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from an external API without specific boundary markers or sanitization logic.
  • Ingestion points: Output from curl requests to the Kong Admin API as documented in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: shell command execution via curl.
  • Sanitization: No validation or sanitization of content returned by the Admin API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:17 PM
Security Audit — agent-trust-hub — kong-gateway