Reference
The vocabulary of AI supply-chain security
Agents introduced a set of artifacts that behave like code, are reviewed like documentation, and appear in no dependency scan. These are the terms that describe them — defined precisely, with the governance consequence spelled out and a primary source on every page.
14 / 14 terms
Nothing matches that. Try a different term or clear the filter.
- Protocol
Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in November 2024, that defines how AI applications connect to external tools and data sources over a JSON-RPC interface.
- Protocol
MCP server
An MCP server is a program that exposes tools, resources, and prompts to AI applications over the Model Context Protocol, running either as a local subprocess or as a remote HTTP service.
- Agent artifacts
CLAUDE.md
CLAUDE.md is a Markdown file that Claude Code loads automatically at the start of a session, giving the model persistent project instructions, conventions, and context.
- Agent artifacts
Agent Skills
An Agent Skill is a folder containing a SKILL.md file — YAML frontmatter plus Markdown instructions — that an AI agent discovers and loads on demand when a task matches its description.
- Controls
Claude Code hooks
Hooks are user-defined shell commands that Claude Code executes automatically at specific lifecycle events, allowing deterministic control over what an agent is permitted to do.
- Threats
Prompt injection
Prompt injection is an attack in which attacker-controlled content is interpreted by a language model as instructions, causing it to act against the operator's intent.
- Threats
Tool poisoning
Tool poisoning is an attack in which malicious instructions are embedded in an MCP tool's description or schema, so the model reads them as guidance while the human sees only a harmless tool name.
- Threats
Rug pull attack
A rug pull attack is when an MCP server or agent artifact behaves benignly during review and then changes its definitions or behaviour after it has been approved and installed.
- Practices
Shadow AI
Shadow AI is the use of AI tools, models, or agent configurations inside an organisation without the knowledge or approval of IT and security.
- Practices
AI supply chain
The AI supply chain is the full set of external artifacts an AI system consumes — models, prompts, skills, rules, hooks, MCP connectors, and retrieved context — each of which can alter its behaviour.
- Practices
AI bill of materials (AI-BOM)
An AI bill of materials (AI-BOM) is a structured inventory of every component an AI system depends on, including models, datasets, prompts, instruction artifacts, and tool connectors.
- Controls
Agent sandboxing
Agent sandboxing is the practice of running an AI agent inside an environment that restricts its filesystem, network, and process access, so that a compromised or misled agent cannot act beyond a defined boundary.
- Threats
Confused deputy problem
The confused deputy problem occurs when a program with legitimate privileges is manipulated by a less-privileged party into misusing that authority on the attacker's behalf.
- Practices
Context window
A context window is the maximum number of tokens a language model can process in a single request, covering the system prompt, conversation history, tool definitions, retrieved content, and the response.
Keep reading
- AI surfacesWhat each AI tool can natively control, and what it leaves open.
- MCP server directoryServers reviewed for what they can reach and what to restrict.
- Agent skills directoryPublished skills reviewed for what they execute in your environment.
- ComparisonsHow this layer differs from gateways and AI security platforms.
Know what your agents load
Vincosha is the control plane for enterprise AI: one signed source for the skills, rules, hooks and connectors every AI surface consumes, scanned before they reach a laptop and attributed per session.