local-server

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill exposes a local FastAPI "execute directive" endpoint and explicitly uses local files/.env while recommending Cloudflare tunneling for external access — together these patterns create a high-risk vector for remote command execution and credential/data exfiltration if exposed or abused.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs opening a Cloudflare tunnel for external webhook access and exposes endpoints like /directive and /general-agent that execute incoming directives, meaning the agent will ingest and act on untrusted third-party webhook content.