bmad-ux
Warn
Audited by Snyk on Jun 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime LLM context can include outsider free text via the “Source scan” + “Subagent-extracts on confirm” path: it ingests user-selected content from
{planning_artifacts}/(e.g., PRDs/issues/wiki/discussion text authored by others) into the distillation/finalization prompts, which then feed the LLM context for generatingDESIGN.md/EXPERIENCE.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata