single-cell-annotation-guide
Warn
Audited by Snyk on Apr 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs fetching and ingesting public third‑party references and models (e.g., "Download them as AnnData from CELLxGENE Census or Zenodo" for popV and selecting models via celltypist.models.models_description()), meaning the agent will read/interpret untrusted external datasets that can materially influence annotation decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata