fold
Warn
Audited by Snyk on Mar 1, 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's scripts and workflow explicitly fetch and parse public FastFold API responses and artifact URLs (see SKILL.md and scripts/fetch_results.py, wait_for_completion.py, download_cif.py and references/jobs.yaml), and public job results/artifacts hosted on artifacts.fastfold.ai can be user-generated and are used to drive polling, downloads, and viewer-link actions, exposing the agent to untrusted third-party content.
Audit Metadata