loop-engineering
Warn
Audited by Snyk on Aug 24, 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 loop’s REQUIRED runtime workflow reads the entire GitHub issue/pull-request thread (and later review comments/CI logs) authored by others as part of Phase 1 intake and subsequent Phases, without requiring the agent to first select a specific outsider-authored item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata