Command
Security
Command
/agt-check
Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors.
Install
> /plugin marketplace add microsoft/agent-governance-toolkit > /plugin install agt-governance@agent-governance-toolkit
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/agt-check
Context preview
What this command does when you run it.
Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors.
Command definition
agt-check.mddescription: Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors. argument-hint: [text] allowed-tools: mcp__agt_governance__agt_policy_check_text
If `$ARGUMENTS` is empty, tell the user to pass text to inspect.
Otherwise, call `mcp__agt_governance__agt_policy_check_text` exactly once with:
{"text":"$ARGUMENTS"}Print the JSON result verbatim. Do not summarize or add commentary.
Ships withagent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Get the whole plugin
Stats
6,405
Stars
1,127
Forks
Active
Maintenance
Python
Language
MIT
License
14h ago
Last commit
7mo ago
Created
9h ago
Added
Repo: microsoft/agent-governance-toolkit