reflect
Warn
Audited by Snyk on Aug 20, 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 reflect workflow ingests the active session transcript (which may include outsider-provided free text) at the reviewers’ step (“Read the active transcript at <ABSOLUTE_PATH>”), without first selecting a specific trusted item, so prompt-injection text can enter the LLM via the transcript.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata