brand-voice
Warn
Audited by Snyk on Nov 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required Auto-Scrape workflow has agents fetch arbitrary web pages, search-discovered podcast/YouTube transcripts, and public social posts (SKILL.md [145]-[148]) that are selected by URL or keyword search rather than arriving in a feed an outsider can push into, so outsider text is exposed only after the agent actively searches or fetches it.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata