autoresearch
Warn
Audited by Snyk on Aug 20, 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.mdthe autoresearch workflow explicitly performs “Search the web for better approaches” in step 2, which ingests outsider-authored free text from arbitrary web pages as part of its runtime research.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata