Skip to content

Glossary

Glossary

Definitions for key terms used throughout the specification. Where a term has a precise technical meaning that differs from common usage, the technical meaning takes precedence within the spec.

Working Draft·version 3.0.0-alpha.1·updated 25 May 2026·canonical /spec·editor Adam Lin

Term Definitions

agent runtime
An execution environment that hosts one or more AI agents and mediates their access to tools, model APIs, and external resources.
ATR engine
An implementation that consumes ATR rules and emits matches. A conforming engine MUST satisfy the requirements in /conformance §1.
ATR rule
A single YAML document declaring an attack pattern, the field it inspects, its test cases, and its cross-framework mappings.
canary
A 24-hour observation window during which a newly generated rule runs in shadow mode before being eligible for production status.
conformance level
One of L1 (Engine), L2 (Publisher), or L3 (Sub-range Authority). Defined normatively in /conformance.
crystallization
The Threat Cloud pipeline that converts an observed attack into a candidate ATR rule and routes it through review.
detection.conditions
The array of field/operator/value triples in a rule body that determine whether the rule matches.
fixture
A YAML file under spec/conformance/ pairing a rule with its expected evaluation outcome on a fixed event.
Implementer Report
A self-declared public record of an organization's ATR integration, listed on /implementers.
informative
Content that provides context but does not define conformance requirements.
maturity
The promotion stage of a rule: experimental → test → stable. Promotion rules are defined in RFC-001.
MCP exchange
A single request/response pair between an MCP client and an MCP server. ATR rules with scan_target: mcp_exchange evaluate against this shape.
normative
Content that defines requirements for conformance. Engines and rules MUST follow normative sections.
provenance
Metadata on a rule describing who authored it, from what source (e.g., garak probe, CVE), and when.
RFC-001
The internal numbering of ATR's quality standard for rule promotion. See /quality-standard.
scan_target
A required field on every rule declaring what shape of event the rule expects: skill, mcp_exchange, agent_config, etc.
severity
One of {informational, low, medium, high, critical} declared on every rule.
SKILL.md
A Markdown manifest format used by some MCP skill ecosystems (OpenClaw, Skills.sh, ClawHub) to declare an agent skill's tools, prompts, and metadata.
status
A required field on every rule: draft, stable, deprecated. Rules with status: draft MUST NOT participate in production matching without explicit opt-in.
sub-range
A contiguous segment of the ATR-YYYY-NNNNN identifier space reserved for a specific publisher (e.g., ATR-TW-2026-NNNNN for Taiwan).
Technical Steering Committee (TSC)
The body that governs ATR's evolution. Currently in BDFL transition; see /charter.
Threat Cloud
ATR's auto-review backend for community-submitted rules. Runs the crystallization pipeline and safety gates.

Editor: Adam Lin <[email protected]> — DOI 10.5281/zenodo.19178002 — MIT License — ISO 8601 2026-05-25