bmad-build
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). Outsider-authored text is ingested as “intent” via the parent message (step-01 clarifies/routs it), and that intent can drive loading/compiling planning artifacts (e.g., compile-epic-context reads epics/planning files) which then become LLM-readable context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata