wos-parse-results

Warn

Audited by Snyk on Mar 6, 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 ingests Web of Science results—parsing NDJSON from the runQuerySearch API (Mode A) and DOM-scraping the public results page via app-record selectors (Mode B) as shown in SKILL.md—so it reads third-party webpage/API content that could materially influence downstream actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 09:38 AM