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

ASI01: Memory Poisoning

Adversarial entries injected into long-term agent memory persist across sessions.

Last reviewed July 2026

The gap ASI01 closes

In OWASP Agentic Top 10, Memory Poisoning addresses memory. Adversarial entries injected into long-term agent memory persist across sessions. Penaxtra records this control at high 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 ASI01

Penaxtra ships adversarial probe families that target memory poisoning 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 ASI01 identifier. The OWASP Agentic Top 10 ASI01 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.

ASI01 capabilities

Probe and check coverage aligned to ASI01 (Memory Poisoning)

Findings tagged with the OWASP Agentic Top 10 ASI01 identifier

Penaxtra severity for this control (high)

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

PDF and JSON evidence export with the control identifier attached

ASI01 compliance mapping

Findings for ASI01 carry the OWASP Agentic Top 10 ASI01 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 ASI01 (Memory Poisoning)?

Adversarial entries injected into long-term agent memory persist across sessions. It is a OWASP Agentic Top 10 control; Penaxtra assesses it at high severity.

How does Penaxtra test for ASI01?

Penaxtra ships adversarial probe families that target memory poisoning 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 ASI01 identifier.

Does a finding for ASI01 help with an audit?

Each finding is tagged with the OWASP Agentic Top 10 ASI01 identifier and exported in the PDF and JSON evidence pack, so it appears on the auditor control list with the identifier already attached.