scenic-gene-regulatory-network

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly instructs downloading and loading public cisTarget ranking databases and motif files from resources.aertslab.org (see "Database downloads (CRITICAL)" wget commands and the db_glob/motif_path usage in SKILL.md), which are untrusted third‑party files the agent reads and uses to prune regulons and drive downstream analysis—so external content can materially change behavior.