academic-pipeline
Warn
Audited by Snyk on Aug 16, 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 only observer that reads outsider-authored free text is the
collaboration_depth_agent, which at FULL/SLIM checkpoints reads the live dialogue turns (user messages) and is explicitly advisory-only, never blocking, but it still ingests user-submitted text at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata