x-research
Warn
Audited by Snyk on Jul 5, 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). Phase 1/2 uses
site:x.comweb search results and extracts “要約” from the fetched tweet text (outsider-authored public X posts), which is then placed into the agent’s LLM context during Phase 4 reporting.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata