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” skill reads the active conversation transcript from the workspace
agent-transcripts/JSONL files, which contain outsider-authored free text (the user’s messages) and then fans it out into reviewer subagents at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata