server-monitor

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow step "Probe endpoints" together with the webfetch tool and the example endpoint in automation.example.yaml ("https://api.example.com/health") show the agent will fetch and interpret external HTTP endpoint responses as part of its decision-making, so untrusted third-party content could influence actions.