Our engineers set up and run your first chatbot / LLM security scan. Get in touch

ASI10: Overreliance

Human-in-the-loop bypasses the safety net by rubber-stamping agent decisions.

Last reviewed July 2026

The gap ASI10 closes

In OWASP Agentic Top 10, Overreliance addresses human oversight. Human-in-the-loop bypasses the safety net by rubber-stamping agent decisions. Penaxtra records this control at medium severity and establishes its state by exercising it against the running system, so the result reflects observed behavior rather than a documented assertion.

How Penaxtra delivers ASI10

Penaxtra ships adversarial probe families that target overreliance directly. Each probe runs against the live endpoint on a schedule, and every triggering response is scored by three independent judges and a meta-judge before it is recorded as a finding under the ASI10 identifier. The OWASP Agentic Top 10 ASI10 identifier is attached when the finding is created, so it appears in the exported evidence pack already mapped to the control. Where the same weakness maps to another framework, the finding carries those control identifiers as well.

ASI10 capabilities

Probe and check coverage aligned to ASI10 (Overreliance)

Findings tagged with the OWASP Agentic Top 10 ASI10 identifier

Penaxtra severity for this control (medium)

Cross-framework identifiers attached to the same finding where controls overlap

PDF and JSON evidence export with the control identifier attached

ASI10 compliance mapping

Findings for ASI10 carry the OWASP Agentic Top 10 ASI10 identifier along with the corresponding control identifiers in the other frameworks Penaxtra maps, so one result is reflected across each mapped framework.

Frequently asked

What is ASI10 (Overreliance)?

Human-in-the-loop bypasses the safety net by rubber-stamping agent decisions. It is a OWASP Agentic Top 10 control; Penaxtra assesses it at medium severity.

How does Penaxtra test for ASI10?

Penaxtra ships adversarial probe families that target overreliance directly. Each probe runs against the live endpoint on a schedule, and every triggering response is scored by three independent judges and a meta-judge before it is recorded as a finding under the ASI10 identifier.

Does a finding for ASI10 help with an audit?

Each finding is tagged with the OWASP Agentic Top 10 ASI10 identifier and exported in the PDF and JSON evidence pack, so it appears on the auditor control list with the identifier already attached.