news-collection
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The only “outsider” free text source described in the required runtime workflow is public/external article content extracted from URLs/feeds in Phase 1 (e.g., meta/byline/body used to populate the five-fact contract); this is then fed into the agent (including subagent dispatch in Phase 2) as item text excerpts and fields, creating indirect prompt-injection exposure.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata