web-fetch

Warn

Audited by Snyk on Apr 17, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and scripts/web_fetch.py explicitly accept arbitrary URLs via --url or piped stdin and use a headless Chrome CDP session to fetch and extract full page text from those public webpages (e.g., fetch_page in scripts/web_fetch.py), meaning untrusted third‑party content is ingested and returned for downstream use, enabling indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 17, 2026, 06:55 PM
Issues
1