article-extractor
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow fetches and parses user-supplied URLs (e.g., via
reader "$ARTICLE_URL"/trafilatura --URL "$ARTICLE_URL"/curl -s "$ARTICLE_URL" | python3 ...), ingesting outsider-authored web page text into the LLM context as readable extracted article content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata