# Delx Security index

Delx Security is the defensive assurance arm of the Delx ecosystem.

## Human pages

- [Home](https://security.delx.ai/)
- [Services](https://security.delx.ai/services)
- [Start a review](https://security.delx.ai/start)
- [Assurance method](https://security.delx.ai/method)
- [Research method](https://security.delx.ai/research)
- [Vulnerability disclosure](https://security.delx.ai/disclosure)
- [Privacy](https://security.delx.ai/privacy)

## Assessment answers

- AI agent security assessment: a bounded review of identity, authority, tools,
  context, egress, evidence and recovery.
- Evidence map: identity and authority, tools and side effects, context and
  memory, and failure and recovery tied to observable proof.
- MCP security review: an authorized review of discovery, schemas,
  authentication, validation, side effects, egress, secrets and revocation.
- [Services and engagement boundaries](https://security.delx.ai/services)

## Field guides

- [AI agent threat modeling](https://security.delx.ai/guides/ai-agent-threat-model)
- [AI agent security review](https://security.delx.ai/guides/ai-agent-security-review)
- [MCP security checklist](https://security.delx.ai/guides/mcp-security-checklist)
- [MCP authorization security](https://security.delx.ai/guides/mcp-authorization-security)
- [AI agent security controls](https://security.delx.ai/guides/ai-agent-security-controls)
- [Prompt injection defense](https://security.delx.ai/guides/ai-agent-prompt-injection-defense)
- [Supply-chain security](https://security.delx.ai/guides/ai-agent-supply-chain-security)
- [Incident response](https://security.delx.ai/guides/ai-agent-incident-response)
- [Shared-computer boundaries](https://security.delx.ai/guides/ai-agent-shared-computer-boundaries)

## Machine-readable contracts

- [LLM context](https://security.delx.ai/llms.txt)
- [Full LLM context](https://security.delx.ai/llms-full.txt)
- [Agent entry points](https://security.delx.ai/agents.txt)
- [Authorized assurance playbook](https://security.delx.ai/skill.md)
- [Direct answers](https://security.delx.ai/answers.txt)
- [Sitemap](https://security.delx.ai/sitemap.xml)
- [Vulnerability disclosure contract](https://security.delx.ai/.well-known/security.txt)
- [Authentication boundary](https://security.delx.ai/auth.md)
- [Agent Skills index](https://security.delx.ai/.well-known/agent-skills/index.json)
- [OAuth Protected Resource Metadata](https://security.delx.ai/.well-known/oauth-protected-resource)

## Boundaries

All security work is defensive and explicitly authorized. Public guidance does
not grant testing permission and does not claim certification, customers,
guaranteed security or a legal entity without public evidence.

Contact: support@delx.ai