bmad-eval
Warn
Audited by Snyk on Oct 12, 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 user-authored query strings from
evals/triggers.jsonand inputs from case files (evals/cases.json) and runs them through the harness, exposing the agent to untrusted/outsider-authored test cases.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata