site-ranking

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's main workflow (SKILL.md and scripts/run_site_ranking.py) explicitly fetches and ingests data from public third‑party APIs (ClinicalTrials.gov API v2 via _search_clinical_trials and OpenAlex via _standardize_sites_openalex), and those untrusted, user-contributed fields (facility names, contacts, publications, etc.) are parsed and used to build/rank the network, meaning external content can materially influence the agent's outputs and subsequent decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 06:55 AM