jet-rebuttal
Warn
Audited by Snyk on Jun 25, 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). The required workflow ingests JET editor/referee reports (single-anonymized referee comments) as free-form text at runtime, which are outsider-authored and then quoted into the agent’s LLM context via the “Show the diff / Quote each comment” response-letter skeleton.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata