slack-expert
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill ingests and processes user-generated Slack content (e.g., app_mention events, Conversations API messages, Files API content and other workspace messages) via the Events/Conversations/Files APIs, which are third-party user-provided inputs the agent is expected to read and could carry indirect prompt-injection payloads.
Audit Metadata