Research
AI Model Risk Depends on What the Model Can Reach
First reported · Discovered snyk.io
Page published
Earliest dated coverage: 21 Oct 2026 · First observed: 22 Oct 2026 · Latest dated coverage: 21 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Snyk’s findings highlight why defenders must combine model-level adversarial scores with deployment status, accessible data, and permitted actions to prioritize actual application risk.
Snyk research matched model identifiers in 1,693 enterprise environments to adversarial tests covering 29 attacker goals, finding that 49.2% referenced a model with at least one critical score. PII extraction and command execution accounted for critical findings, but the study does not establish production exposure or successful attacks against those applications. Only 37.5% of detected model occurrences had matched scores.