brief
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md describes scanning connected sources like Email and Chat for “overnight messages,” “direct messages,” and “real-time discussions,” which are outsider-authored free text from other people, and then synthesizing those findings into the LLM’s briefing output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata