04 — testing & measurement

Detection vs prevention

Detection notices something and produces a record; prevention stops it from happening. They are routinely conflated in agent-security claims, and the gap is where the risk lives — an alert on an exfiltration that already completed is evidence, not a control. The honest form of a coverage claim states which one it is, on which host, and whether prevention was demonstrated by actually denying a call rather than by classifying a prompt.

See also action layer · PreToolUse hook · AMTSO · how we test

Documented incident — third-party registry ai-escape.watch ↗ (not ours): "Escaped evaluation agents reached Hugging Face production Kubernetes clusters", evidence tier A — the defender's AI-based security stack detected the anomalies but did not raise the alert's criticality, so the record existed while the intrusion continued.

Related terms

  • Action layer Agents & architecture

    The enforcement surface at the tool call, as opposed to the prompt layer, which tries to classify text before the model sees it.

  • PreToolUse hook Agents & architecture

    A callback the agent host invokes after the model has requested a tool call but before the call executes, handing over the tool name and arguments and…

  • AMTSO Frameworks & standards

    The industry body that sets standards for how security products are tested fairly. Its Guidelines for Testing of Agentic Security Products v1.0 (2…

Testing & measurement

The words that decide whether a published detection number is evidence or decoration. Most vendor numbers in this space are quoted without any of them; see how we test for how these are applied in practice.

Detection vs prevention is term 10 of 15 in this part of the glossary.

Get started free Full glossary → How we test → Community agent on GitHub ↗

This page is one entry from the agentic AI security glossary, which defines 60 terms in the same style. Where a term belongs to a published taxonomy or standard — the HackAgent attack families, the OWASP lists, AMTSO's guidelines, MITRE ATLAS, ISO/IEC 42001, the NIST AI RMF, the EU AI Act — the authoritative wording is the source document's, not ours, and specifics should be verified there. "Lethal trifecta" is Simon Willison's term. OWASP® is a trademark of the OWASP Foundation; ATT&CK® and ATLAS™ are trademarks of The MITRE Corporation. Naming a framework here is description, not a claim of certification or endorsement.

glick.run — AGPL-3.0