brand-voice
Warn
Audited by Snyk on Sep 1, 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 involves gathering posts, essays, or social media content (such as X posts via
x-api) to build a voice profile, which exposes the agent to user/outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata