AI safety and cybersecurity trackers: what are teams missing?

TL;DR: Prompt injection, input manipulation, model extraction, insecure plugins, supply chain compromise, and agentic manipulation now span the full attack lifecycle across AI systems, according to Asenion's AI Safety+Cybersecurity R&D Tracker. The key governance shift is that AI security has become an access, integrity, and exfiltration problem, not just a model-quality problem.

Editorial analysis by NHI Mgmt Group, based on content published by Asenion: “AI Safety+Cybersecurity R&D Tracker”.

Key questions

Q: What breaks when indirect prompt injection is not controlled in AI systems?

A: Indirect prompt injection breaks the assumption that retrieved content is safe to use as instruction material.

Q: Why do AI agents increase non-human identity risk?

A: AI agents increase non-human identity risk because they can execute many actions quickly once they inherit a credential or tool permission.

Q: How can security teams tell if AI output is becoming a security control gap?

A: A control gap appears when generated text, code, or commands are used without review in systems that can store data, execute actions, or change permissions.

Practitioner guidance

• Separate instructions from content Design AI workflows so system prompts, retrieved content, and user inputs are handled as distinct trust classes, with untrusted content unable to override policy instructions.
• Constrain agent permissions by task Limit tool use, connector scope, and token reach so an AI agent can only access the minimum accounts and actions needed for the current session or workflow.
• Inspect outputs before downstream execution Require validation on AI-generated text, code, and commands before those outputs are stored, executed, or passed into business systems that can change state.

Bottom line: AI safety taxonomies now map cleanly to access, integrity, and exfiltration risks, which means governance has to move beyond model-quality checks.

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →