Cisco AI agent security
Cisco combines open-source and commercial pieces. The DefenseClaw documentation says its guardrail checks a prompt, a shell command or a tool call before the agent acts, with fail-closed defaults, and marks support on Linux, macOS and Windows only after a live test. The AI Defense plugin for Kong Gateway inspects LLM and MCP requests, and audit logs export to Splunk or OpenTelemetry. Code is Apache-2.0 and an Explorer Edition is described as free. Cisco says agent identity and its MCP gateway are still in development, and a central agent inventory is noted as in development. Browser agents and Copilot Studio, Agentforce or ServiceNow coverage: none found on 16 Nov 2026.
Facts read on .
Strength and weakness for AI Agent Security Solutions
Strength: Covers endpoint hooks on many named coding agents on three operating systems plus a gateway plugin and audit export to Splunk or OpenTelemetry (cisco-10, cisco-11, cisco-05, cisco-17).
Weakness: None found on 2026-11-16 for browser agents or named SaaS agent platforms, and Cisco says agent identity and MCP gateway features are still in development (cisco-46, cisco-47, cisco-41).
Scores and evidence
Cisco is 10th in the overall ranking at 57.0 of 100. Each score below lists the fact ids behind it; the facts follow further down with their sources and read dates.
| Criterion | Score | Weight | Why | Facts |
|---|---|---|---|---|
| Coverage: endpoint layer | 7 of 10 | 6 | Documented hooks for named coding agents block tool calls and shell commands, live-tested per OS; vendor documentation only. | cisco-10, cisco-11, cisco-12, cisco-14 |
| Coverage: browser layer | 1 of 10 | 6 | Only network-based shadow AI detection; browser agent coverage none found. | cisco-47, cisco-48 |
| Coverage: cloud workspace layer | 5 of 10 | 6 | AgentCore, Strands and Google ADK inspection exist, the ADK plugin observed; Copilot Studio, Agentforce and ServiceNow none found. | cisco-43, cisco-44, cisco-45, cisco-46 |
| Coverage: identity layer | 6 of 10 | 6 | Placeholder credentials and task-scoped privileged access exist; agent registration is reported by third parties as planned. | cisco-15, cisco-39, cisco-40, cisco-55 |
| Coverage: gateway layer | 6 of 10 | 6 | A Kong plugin inspects LLM and MCP traffic and fails closed; the MCP gateway is in development. | cisco-05, cisco-07, cisco-41 |
| Stops the action | 7 of 10 | 20 | Prompts, shell commands and tool calls are checked before acting with fail-closed defaults; the docs state a limit on child processes. | cisco-02, cisco-05, cisco-09, cisco-10, cisco-20 |
| Visibility | 5 of 10 | 15 | Decision logs exist, but the central agent inventory is noted as still in development. | cisco-17, cisco-42, cisco-43 |
| Deployment | 6 of 10 | 10 | Network enforcement and package or MDM rollout are documented; a time to deploy for the runtime product none found. | cisco-04, cisco-38 |
| Policy and governance | 6 of 10 | 10 | Group-based policy and OpenTelemetry and webhook log export are documented; IdP and ticketing integrations none found. | cisco-16, cisco-17, cisco-18, cisco-53 |
| Transparency | 6 of 10 | 10 | Documentation and Apache-2.0 code are public with a free edition; a paid list price none found. | cisco-29, cisco-56, cisco-57 |
| Proof | 5 of 10 | 5 | Third-party coverage and one named customer voice; analyst coverage none found for this line. | cisco-58, cisco-60, cisco-59 |
Where it ranks
| View | Rank | Total |
|---|---|---|
| Overall ranking | 10th | 57.0 |
| Ranked for the endpoint layer | 7th | 63.0 |
| Ranked for the browser layer | 12th | 45.0 |
| Ranked for the cloud workspace layer | 10th | 57.0 |
| Ranked for the identity layer | 7th | 60.0 |
| Ranked for the gateway layer | 10th | 60.0 |
Product, deployment, price and owner
- Product assessed: Cisco AI Defense (runtime guardrails, AI Cloud Visibility, Explorer red teaming) with open-source DefenseClaw and Duo IAM agent registration (in development)
- Deployment: Network-level enforcement without agents or libraries for AI Defense; Kong plugin, Python SDK, command-line MCP Scanner, and DefenseClaw hooks installed per user or by MDM package
- Time to deploy: Cisco says DefenseClaw installs in about five minutes (SiliconANGLE); none found on 2026-11-16 for AI Defense
- Price: none found on 2026-11-16 (paid AI Defense); Explorer Edition is described as free
- Owner: Cisco Systems, Inc.
- Website: cisco.com
Facts and sources
cisco-01 (vendor): Cisco Systems, Inc. is the owner and copyright holder of DefenseClaw, the open-source agent governance layer published in the cisco-ai-defense GitHub organization alongside AI Defense.
The exact quote is on the source page.
Source: github.com, read .
cisco-02 (vendor): Cisco says AI Defense runtime protection puts guardrails in the network and blocks adversarial attacks and harmful responses in real time.
Quote: "Protect production AI applications with guardrails embedded in the network. Block adversarial attacks and harmful responses in real time."
Source: cisco.com, read .
cisco-04 (vendor): Cisco says AI Defense enforces at the network level, with no agents or libraries needed on the application side.
Quote: "Cisco enforces AI security at the network-level without the need for agents or libraries."
Source: cisco.com, read .
cisco-05 (vendor): The AI Defense Intercept plugin for Kong Gateway inspects AI/LLM and MCP requests and responses and blocks or forwards traffic on the AI Defense verdict.
Quote: "It blocks or forwards traffic based on the AI Defense verdict."
Source: github.com, read .
cisco-07 (vendor): The Kong plugin fails closed by default: traffic is blocked when inspection is unavailable, and an operator can set it to fail open.
Quote: "Block traffic when inspection is unavailable."
Source: github.com, read .
cisco-09 (vendor): Cisco says DefenseClaw endpoint hooks fail closed by default, with Cisco Secure Client deployments defaulting to fail open when no policy is specified.
Quote: "Only Cisco Secure Client deployments default hook delivery to fail-open when no policy is specified"
Source: github.com, read .
cisco-10 (vendor): DefenseClaw documentation says its guardrail checks a prompt, a shell command or a tool call before the agent acts and answers allow, alert, ask or block.
Quote: "The guardrail checks what your agent is about to do (a prompt, a shell command, a tool call) against rules, and answers allow, alert, ask you, or block."
Source: cisco-ai-defense.github.io, read .
cisco-11 (vendor): DefenseClaw documentation says support on Linux, macOS and Windows is marked Supported only after a live test verified hooks and a block before the tool call ran.
Quote: "means a live test on that OS verified the agent's hooks and a block before the tool call ran."
Source: cisco-ai-defense.github.io, read .
cisco-12 (vendor): The DefenseClaw compatibility table lists hook contracts for Claude Code that inspect prompts, tool calls and tool results, with similar rows for Codex, Cursor, GitHub Copilot CLI and others.
Quote: "Claude Code | `>=2.1.154, <2.1.219` | `claudecode-hooks-v1` / `v7` | 28 | prompt, tool_call, tool_result, event_content"
Source: cisco-ai-defense.github.io, read .
cisco-13 (vendor): On 2026-10-21, Cisco said DefenseClaw checks every prompt, tool call and tool result in an NVIDIA OpenShell sandbox using its own rules and Cisco AI Defense.
Quote: "Every prompt, tool call and tool result is checked and observed by DefenseClaw’s rules and by Cisco AI Defense."
Source: blogs.cisco.com, read .
cisco-14 (vendor): On 2026-10-21, Cisco said DefenseClaw decides each web destination for a sandboxed coding agent by host name without decrypting traffic, which covers outbound network calls.
Quote: "DefenseClaw decides each web destination by host name, without decrypting the traffic."
Source: blogs.cisco.com, read .
cisco-15 (vendor): On 2026-10-21, Cisco described the sandbox as supplying provider credentials only for authorized requests, so the agent sees placeholders instead of real credentials.
Quote: "Provider credentials are supplied only for authorized requests; inside the sandbox, the agent sees placeholders."
Source: blogs.cisco.com, read .
cisco-16 (vendor): On 2026-10-21, Cisco said enterprise administrators can set user- or group-based policy for which coding agents run on managed endpoints and which run only in a sandbox.
Quote: "Enterprise administrators can configure user or group-based policy to determine which coding agents can run on their managed endpoints"
Source: blogs.cisco.com, read .
cisco-17 (vendor): On 2026-10-21, Cisco said every block, approval and decision is recorded with the agent, sandbox and policy behind it and can be sent to Splunk or any OpenTelemetry backend.
Quote: "Every block, approval and decision is recorded along with the agent, the sandbox and the policy behind it, and can be sent to Splunk or any OpenTelemetry backend."
Source: blogs.cisco.com, read .
cisco-18 (vendor): DefenseClaw observability documentation lists OTLP, Splunk, Galileo, file and webhook destinations for logs, traces and metrics.
Quote: "goes to the destinations you add: an OpenTelemetry (OTLP) collector, Splunk, Galileo, a file, or a webhook."
Source: cisco-ai-defense.github.io, read .
cisco-19 (vendor): DefenseClaw documentation says human approval is off by default, with a default minimum severity of HIGH when turned on.
Quote: "Human approval is off by default. Its default minimum severity is HIGH."
Source: cisco-ai-defense.github.io, read .
cisco-20 (vendor): DefenseClaw documentation states a limit: its command-text check cannot see what a child program writes after a command starts, so protected files need a sandbox or file permissions.
Quote: "It cannot see what a child program writes after a command starts. For protected files, add a sandbox or file permissions."
Source: cisco-ai-defense.github.io, read .
cisco-27 (vendor): The MCP Scanner runs as a stand-alone command-line tool or a REST API server, installed with uv.
Quote: "Run scanner as a stand-alone CLI tool or REST API server"
Source: github.com, read .
cisco-29 (vendor): DefenseClaw documentation says its public website is the source of truth for install, configuration and operator workflows, and the code is Apache-2.0.
Quote: "is the source of truth for installation, setup, configuration, commands, and operator workflows"
Source: github.com, read .
cisco-31 (third-party): On 2026-03-23, SiliconANGLE reported DefenseClaw lets administrators block specific MCP servers, with block rules applied in two seconds without restarting agents.
Quote: "A permission management feature enables administrators to block specific MCP servers."
Source: siliconangle.com, read .
cisco-33 (third-party): SiliconANGLE reported developers can install DefenseClaw in about five minutes and that it scans MCP tools and plug-ins an agent uses.
Quote: "Cisco says developers can install DefenseClaw in about five minutes."
Source: siliconangle.com, read .
cisco-35 (vendor): Cisco says DefenseClaw streams every scan result, block decision, tool call and alert as structured events.
The exact quote is on the source page.
Source: blogs.cisco.com, read .
cisco-38 (vendor): DefenseClaw documentation describes an enterprise edition that an administrator deploys with a package or an MDM and that users cannot turn off.
Quote: "the managed standalone profile an administrator deploys with a package or an MDM. Users can't turn it off."
Source: cisco-ai-defense.github.io, read .
cisco-39 (third-party): CRN reported at RSAC 2026 that Cisco plans to let customers register agents in Duo IAM mapped to human workers, with Identity Intelligence discovering agent identities.
Quote: "register agents in Duo IAM, with the agents then mapped to accountable human workers"
Source: crn.com, read .
cisco-40 (third-party): SiliconANGLE reported on 2026-03-23 that Cisco's planned Duo IAM agent controls can limit an agent's tool access to specific time frames.
Quote: "Agents’ tool access can be limited to specific time frames."
Source: siliconangle.com, read .
cisco-41 (vendor): Cisco says its planned MCP gateway applies authorization policies across tools and blocks out-of-bounds agent actions, but also says the features are in development.
Quote: "the MCP gateway applies authorization policies consistently across tools and services."
Source: blogs.cisco.com, read .
cisco-42 (vendor): Cisco says it discovers and registers AI agents, MCP servers and tools into a central inventory, with a note that many features are still in development.
Quote: "Cisco discovers and registers AI agents, MCP servers, and associated tools"
Source: blogs.cisco.com, read .
cisco-43 (vendor): Cisco says AI Cloud Visibility inventories AI models and connected data sources across a distributed environment.
Quote: "Automatically inventory the AI models and connected data sources across your distributed environment to understand usage and gauge risk."
Source: cisco.com, read .
cisco-44 (vendor): The AI Defense Python SDK README says it can inspect AWS AgentCore and Strands event streams, releasing events only after server acknowledgement.
Quote: "Inspect AgentCore, Strands, and adapter-based provider streams, releasing events only after server acknowledgement."
Source: github.com, read .
cisco-45 (observed): The GitHub org lists a Cisco AI Defense plugin for Google ADK that does callback-based LLM and MCP inspection, plus LangChain and LiteLLM integrations.
The exact quote is on the source page.
Source: api.github.com, read .
cisco-46 (none-found): None found on 2026-11-16: named coverage of Microsoft Copilot Studio, Salesforce Agentforce or ServiceNow agents on the AI Defense product page, Kong plugin, SDK or DefenseClaw docs read.
Source: cisco.com, read .
cisco-47 (none-found): None found on 2026-11-16: coverage of browser agents, AI browsers or AI browser extensions on the AI Defense product page or DefenseClaw connector and support pages.
Source: cisco.com, read .
cisco-48 (vendor): Cisco AI Access, part of Secure Access SSE, inspects web traffic to identify shadow AI use; it is network-based rather than a browser-agent control.
Quote: "AI Access inspects web traffic to identify uses of shadow AI across your organization."
Source: cisco.com, read .
cisco-53 (vendor): On 2026-10-28, Cisco said its Project Quarry detection language is in production in AI Defense and maps findings to alert, block, redact, quarantine or log.
Quote: "Call Quarry from the application path and map findings to alert, block, redact, quarantine, or log."
Source: blogs.cisco.com, read .
cisco-54 (vendor): On 2026-11-09, Cisco published a blog titled 'Cisco AI Defense to Add Anthropic's Claude Mythos for AI Red Teaming'.
Quote: "Cisco AI Defense to Add Anthropic’s Claude Mythos for AI Red Teaming"
Source: blogs.cisco.com, read .
cisco-55 (third-party): On 2026-10-26, SiliconANGLE reported Cisco launched Privileged Infrastructure Access, applying task-scoped rules to AI agents as to people, after an August Teleport partnership and stake.
Quote: "AI agents and automation scripts work under the same task-scoped rules as people"
Source: siliconangle.com, read .
cisco-56 (none-found): None found on 2026-11-16: a published price for Cisco AI Defense on its product page; the free Explorer Edition is announced but no paid list price was found.
Source: cisco.com, read .
cisco-57 (third-party): CRN reported that at RSAC 2026 Cisco introduced a free Explorer Edition of AI Defense for red teaming agents.
Quote: "Cisco also debuted updates to its AI Defense offering with the introduction of a free “Explorer Edition.”"
Source: crn.com, read .
cisco-58 (vendor): The AI Defense product page quotes Kent Noyes of World Wide Technology, a named customer voice.
Quote: "The adoption of AI exposes companies to new risks that traditional cybersecurity solutions don't address."
Source: cisco.com, read .
cisco-59 (none-found): None found on 2026-11-16: independent analyst coverage (Gartner, Forrester, IDC) or a funding round for AI Defense on the pages read; Cisco is a public company.
Source: cisco.com, read .
cisco-60 (third-party): SiliconANGLE covered the 2026-03-23 DefenseClaw release at RSAC 2026 and the Explorer Edition.
Quote: "The networking giant also released an open-source tool, DefenseClaw, that can scan AI agents for vulnerabilities."
Source: siliconangle.com, read .