twilio-conversations-classic-api

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md shows the agent receiving and reading untrusted, user-generated content via Twilio Conversations webhooks (conversations/webhook handling) and fetching message history (messages.list and printing message.body), which the skill ingests and can drive automated responses, so third-party messages could indirectly inject instructions.