look-into-it
Warn
Audited by Snyk on Oct 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill reads chat threads from platforms like Slack via MCP tools (e.g.,
slack_read_thread), ingesting outsider-authored free text from chat channels into the agent's runtime workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata