phyllo
Warn
Audited by Snyk on May 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches creator data from public platforms (see SKILL.md: "Phyllo ... access creator data from various platforms like YouTube, TikTok, and Instagram") via Membrane actions (e.g.,
membrane action run ...whoseoutputthe agent is expected to read), so untrusted, user-generated third‑party content can be ingested and influence subsequent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata