web-to-markdown
Warn
Audited by Snyk on Jul 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md:13-18 instructs fetching arbitrary user-provided web page content at runtime (public web content via
curl https://r.jina.ai/...), which is outsider-authored free text that can be ingested into the agent/LLM context as Markdown.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata