llm-wiki
Warn
Audited by Snyk on Jul 1, 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). Outsider free text can enter the LLM context via the URL-ingest runtime path
bash scripts/ingest-url.sh ... <URL>which uses the Scrapling CLI to fetch and extract arbitrary public web page content intoraw/sources/*.mdand then the agent reads/synthesizes that text intowiki/sources/*.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata