slack
Warn
Audited by Snyk on Mar 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly includes actions like "readMessages" and other reads (reactions, pins, memberInfo) that ingest user-generated Slack channel/DM content (third-party, untrusted) which the agent can read and then act on (react, pin, send, edit, delete), so messages could carry instructions that influence behavior.
Audit Metadata