# LLM security tools

The stack that protects LLM applications: input/output filters, firewalls and gateways, runtime enforcement, red teaming, and observability. No single tool covers all five.

Learn more: [LLM Security Tools](/content/learn/llm-security-tools/index.html)

Part of [the Agent Control Fabric](/content/platform/index.html): Highflame's identity, policy, and enforcement substrate for AI agents.

## Keep exploring the glossary.

### MCP (Model Context Protocol)
An open protocol that connects agents to external tools and data. Powerful for capability. But every connection is a new access path that has to be governed.  
Read → [Link](/content/glossary/mcp/index.html)

### MCP Gateway
A governed checkpoint every tool connection passes through (authenticated, policy-checked, and logged) so credentials stay central and unapproved servers can't connect.  
Read → [Link](/content/glossary/mcp-gateway/index.html)

### Mission drift
When a non-deterministic agent gradually diverges from its intended task. Tracked at runtime so it can be contained before consequences land.  
Read → [Link](/content/glossary/mission-drift/index.html)

### Non-human identity (NHI)
Identities belonging to machines, services, and agents rather than people. Agents are the fastest-growing and least-governed class of NHI.  
Read → [Link](/content/glossary/nhi/index.html)

### On-behalf-of (OBO) chain
The unbroken provenance recorded on a credential (who authorized the action, what scope was granted, and how deep the delegation goes) so an audit walks back to a human.  
Read → [Link](/content/glossary/obo-chain/index.html)

### Prompt injection
An attack that manipulates an agent through crafted input (in a prompt, a tool result, or retrieved content) to make it act against policy.  
Read → [Link](/content/glossary/prompt-injection/index.html)