crw-dynamic-search
Warn
Audited by Snyk on Aug 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required workflow explicitly fetches and ingests outsider-authored web page text at runtime via
crw scrape r['url'] --format json(and also initial search result text viacrw search ... --json), then prints a filtered subset into context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata