slack

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly reads and ingests user-generated Slack content (e.g., channels/messages via conversations.history and conversations.list, and files via files.info/files.uploadV2) as specified in SKILL.md, exposing the agent to untrusted third-party content that could carry indirect prompt injections.