slack
Warn
Audited by Snyk on Mar 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: 0.90). This skill explicitly fetches and ingests Slack workspace content (messages, threads, files, and attachments) via commands like
agent-slack message get/listandagent-slack searchin SKILL.md, which are untrusted user-generated third-party content that the agent reads and can act on (reply/edit/delete/react), enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata