draft-email-responses
Warn
Audited by Snyk on Jul 30, 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 outsider-authored free text from the user's Gmail inbox at runtime by pulling full email threads via
mcp__claude_ai_Gmail__get_thread(FULL_CONTENT) and then uses that content to generate forwards/draft bodies.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata