messaging-gateway-troubleshooting

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow described by SKILL.md and its references concerns operational verification of Hermes and mentions inspecting live session database/logs and platform webhook inputs, which at runtime can include outsider-authored free text submitted via messaging platforms (e.g., webhook message bodies), creating an indirect prompt-injection surface.