← All Articles

The CISO’s AI Agent Security Checklist — 8 Things to Audit This Week

February 19, 2026 · 6 min read
86%
without full approval
8
audit items
1 week
completion time
0
new tools required

1. Full Inventory of Every AI Agent in Production

Maintain comprehensive registries encompassing commercial tools (Copilot, ChatGPT Enterprise), custom-built systems, developer projects, and API-driven agents. Unregistered agents with elevated credentials represent critical breach vectors.

Framework: NIST CSF 2.0 (ID.AM), ISO 27001:2022 (A.5.9), OWASP AI Security

2. Every MCP Server Connection Mapped

Model Context Protocol servers function as trust boundaries requiring complete documentation. Each connection should identify owners, purposes, data classifications, and authentication mechanisms. MCP compromise is prompt injection at the infrastructure level.

3. No Shared API Keys Between Agents and Humans

Dedicated credentials per agent enable action attribution and independent access revocation. Shared keys eliminate audit trail distinction between human and agent activities.

4. Agent Memory Stores Audited for Poisoning

Memory poisoning manipulates persistent agent memory—conversation histories, learned preferences, RAG knowledge bases—to alter future behaviour without code modification. Agents inherently trust their own stored information.

Framework: OWASP Top 10 for LLM (LLM06), MITRE ATLAS (AML.T0020), NIST AI RMF

5. Data Access AND Exfiltration Paths Documented

Document both data access capabilities and all potential exfiltration channels per agent. Traditional DLP tools don’t account for agents’ ability to summarise, paraphrase, encode, or distribute sensitive information across seemingly innocuous outputs.

6. Human Override Procedures Exist and Tested

Kill-switch mechanisms must function independently of agent operation itself. Actual testing—not theoretical validation—proves override capability. Implement quarterly override drills.

7. Agent-to-Agent Communication Chains Logged

Multi-agent architectures require chain-level logging capturing source, destination, full message content, timestamps, and decision rationale. Orchestration creates emergent behaviours invisible in single-agent logs.

8. AI Agent Infrastructure Red-Teamed at Least Once

Agents’ natural language responsiveness creates unique attack surfaces including social engineering vectors that traditional penetration testing omits. Scope should include prompt injection, tool abuse, memory manipulation, data exfiltration, privilege escalation via agent chains.

Scoring

8/8Exceeding 90% of peers
5–7Foundation established; close remaining gaps
< 5Significant blind spots requiring urgent action
Prioritise items 1 and 2 first. You can’t secure agents you haven’t found.

Need help implementing this?

First strategy session is complimentary. We typically respond within 4 hours.