the-reply-classifier
Warn
Audited by Snyk on Aug 14, 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 Reply Classifier turns “pasted raw replies” (user-provided free text that may contain injection-like instructions such as “system:” or other directives) into a worked list and explicitly quotes/handles embedded instructions rather than obeying them, meaning it directly ingests outsider-authored inbound message text at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata