kb
Warn
Audited by Snyk on Aug 13, 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 skill
kb-*family is described as consuming existing OKF knowledge-bundle markdown concepts (including user-supplied bundle content) as untrusted data for progressive disclosure and routing, meaning outsider-authored free text inside bundle.mdfiles can be ingested at runtime by the agent.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata