langextract

Warn

Audited by Snyk on Mar 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: 0.90). The skill explicitly accepts and auto-fetches arbitrary http(s) URLs (see SKILL.md Step 4 and examples using "https://www.gutenberg.org/..." and the API reference parameter fetch_urls=True) and the CLI script (scripts/langextract_extract.py) also allows a --input URL, so untrusted public web content is ingested and directly influences extraction behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 20, 2026, 06:59 AM
Issues
1