hermes-traffic-guardian

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md/SPEC.md explicitly require the skill to "inspect HTTP request/response text up to a bounded byte limit" (Required First Implementation Behavior #4 and SPEC.md detector/Hermes adapter requirements), which means the agent will ingest arbitrary third-party HTTP/HTTPS traffic that can materially influence detections, posture exports, and subsequent actions.