unified-sovereign-operations
Warn
Audited by Snyk on Feb 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). This skill explicitly requires "Source Ingestion: Extract all data from target websites, documents, media, and community platforms (WhatsApp, Gmail, etc.)" in Phase 1 of SKILL.md and includes concrete flows for scraping/automating third‑party platforms (e.g., Suno, WhatsApp, Spotify) in references/MUSIC_DISTRIBUTION.md, so it ingests untrusted user-generated web and social content that the agent is expected to read and act on for decision-making.
Audit Metadata