autoresearch
Warn
Audited by Snyk on Oct 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow instructs the agent to perform web literature searches via Exa, Semantic Scholar, and arXiv during the research bootstrap and when exploring literature, exposing the agent to arbitrary outsider-authored search results and papers.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata