reflect
Warn
Audited by Snyk on Oct 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 workflow reads active transcripts from the workspace transcript store (
SKILL.md, lines 17-20), which contain user prompts and conversation turns authored by users and external actors.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata