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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata