wiki-research-engineering
Warn
Audited by Snyk on Aug 17, 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). The workflow reads
RESEARCH_QUEUE.mdto get#engineeringqueue items (outsider-authored free text if a provider user can post/submit to that queue) and then uses those topics to driveweb_search/intelli_extract, so the agent can ingest outsider text without selecting a specific item beyond the queue entry.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata