TL;DR: Hidden image instructions let vision-language models create attacker-controlled admin access during routine repository deployment, DeepKeep found. VLM guardrails need visual-layer and side-effect controls, because text-only filters can miss unsafe actions that follow a harmless-looking image.
Editorial analysis by NHI Mgmt Group, based on content published by DeepKeep: “InkJect: The Visual Prompt Injection That Text Defenses Were Never Built to Stop”.
Key questions
Q: Why do multimodal models create new privilege risks for IAM teams?
A: Multimodal models can translate hidden instructions into actions that change accounts, roles, or credentials without the user noticing.
Q: What are the signs that OCR-based filtering is failing against image attacks?
A: A common sign is that automated checks report an image as blank, harmless, or unreadable while the model still reacts to embedded instructions.
Q: How should security teams test for visual prompt injection in multimodal AI systems?
A: Test the full input path, not just the model output.
Practitioner guidance
- Constrain repository retrieval sources Limit which public repositories, image hosts, and shared libraries multimodal systems can query during automated tasks, and block retrieval from untrusted asset paths by default.
- Add visual content validation before execution Inspect images for hidden text, low-contrast overlays, and skewed instructions before allowing any model-generated action to proceed.
- Require human approval for account creation Treat any model-driven creation of users, admins, roles, or credentials as a privileged action that needs explicit approval outside the model.
Bottom line: Visual prompt injection turns hidden instructions inside images into an identity and workflow risk, because the model can act on them even when text guardrails would refuse the same instruction.
Glossary terms: Visual prompt injection, Multimodal model, Retrieval-Augmented Workflow, Visual Layer Guardrail
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Visual prompt injection is now an identity governance problem, not only an AI safety problem. The attacker in this case did not compromise the user session or steal the user’s credentials. Instead, the model itself became the execution path for creating an attacker-controlled admin account, which turns model output into an identity event. That is exactly where IAM, PAM, and AI governance intersect. Practitioners need to treat model-driven account creation as a governed privilege act, not a harmless automation outcome.
A few things that frame the scale:
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: What should teams do when a model can create accounts or privileges during a workflow?
A: They should move account creation, role assignment, and other privilege-changing actions out of the model’s direct control. Those steps need separate approval, logging, and policy enforcement so the model can request work without being able to complete side effects silently. Otherwise, a successful task can hide an unauthorized identity change.
👉 Read our full editorial: Visual prompt injection exposes a blind spot in VLM guardrails