golden-chat-single
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested from the Slack export fixture (
fixtures/slack-export/→references/main.md→ the agent reads the message body “frank: Welcome aboard!”), where the message author is not the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata