feed-bloomberg
Warn
Audited by Snyk on Jun 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The runtime path uses
web_searchto ingest search-result metadata (headline + canonicalbloomberg.comURL) from public web content authored by Bloomberg (an outsider), which is then placed into the agent’s LLM context as normalized JSON fields liketitle/published_at.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata