reply-operations-mapping

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to fetch runtime docs from https://docs.reply.io/llms.txt (and then fetch raw .md pages from that docs host) once per session, meaning external content from that URL is fetched at runtime and directly controls endpoint selection and agent behavior.