cite-them-all

Warn

Audited by Snyk on Feb 20, 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 explicitly fetches and ingests content from public third-party literature sources (PubMed/PMC and bioRxiv/medRxiv) — e.g., SKILL.md "Search PubMed ... using search_articles/get_full_text_article" and workflows/04-reference-search.md / workflows/03-existing-refs-check.md describe using get_full_text_article, search_preprints and get_preprint — and the agent is required to read and act on those abstracts/full texts to choose/insert citations, so untrusted third-party content can materially influence its decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 01:40 AM