synthesis-agent-correspondence
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). SKILL.md describes a correspondence-synthesis workflow that may read entire reply threads “including the quoted history under the latest message” at the reply-history gate, meaning the runtime ingests recipient/customer-authored free text from the monitored conversation source.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata