roadmap
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow reads outsider-authored thread inputs (
seed.md,decisions.md, and optionalproposal.md) fromdocs/threads/<...>/and uses their prose to drive the decomposition, which is then fed into the agent’s LLM context for authoringroadmap.md/roadmap-feedback.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata