slack

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly exposes reading and acting on Slack messages (e.g., the readMessages action and message context ids), which are user-generated/untrusted third-party content that the agent is expected to interpret and which can directly influence subsequent tool actions like reacting, sending, editing, or deleting messages.