wenxian

Warn

Audited by Snyk on Mar 15, 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.md mandates fetching and ingesting content from public third-party sources—PubMed (for abstracts/search results), a public GitHub repository (via scripts/sync_share_repo_jcr.sh), and the EasyScholar open API—whose returned text/metadata are read and used to drive selection, ranking, and downstream agent actions, so untrusted external content can materially influence behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 08:19 AM
Issues
1