nlweb-prompts-customization
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md describes fetching NLWeb’s own prompt/template files from GitHub at runtime (e.g.,
docs/nlweb-prompts.md,config/prompts.xml,config/site_types.xml), which are outsider-authored public web content, and those fetched texts are used to construct LLM prompt templates.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata