Agent Reliability Engineering (ARE)
The ARE Incident Database.
33 catastrophic agent failures that actually happened, each one cited, each one indexed onto the OWASP Agentic Security Initiative (ASI) Top 10.
Every entry carries a public source, a permanent identifier, and its OWASP ASI category. Vendors, including the maintainer, may claim coverage of an entry, and a coverage claim must ship a check anyone can run. Claims that stop holding are withdrawn, not reworded.
Coverage claims.
A vendor may claim that its product stops one of these failures. A claim is listed only if it ships a check a stranger can run, the check runs on every push, and a claim that stops holding is withdrawn rather than reworded. The registry does not rank vendors and does not endorse them. It records what was claimed, by whom, and whether the check still passes.
This index is not reserved for the maintainer.
Any vendor may claim coverage, held to the same bar AgentX Core is held to here. Submit a claim and its check through CONTRIBUTING.md.
How these claims are checked.
Every coverage flag above is a claim, and a claim nobody can check is a press release. 11 of the covered entries carry an executable check. A test in the repository scrapes the snippet out of each published entry, runs it in a clean process with no key and no gateway, and asserts two things: that the block fired, and that the tool body never executed. A block that prints a warning while the action still happens is not a block.
It runs on every push and on a weekly schedule, so a future release cannot quietly break a claim that is already published. When a claim stops being true the entry is reclassified, not reworded, and that rule lives in the governance model rather than in a promise. The badge below is the live one. If it ever goes red, it goes red here.
11 published checks, executed on every pushRead the test or read the rule that says a failing claim gets withdrawn, not reworded.
Cite it.
Incidents carry a stable identifier, ARE-2026-001 through ARE-2026-033. The identifier is permanent: an entry that turns out to be wrong is marked, never deleted and never renumbered, so a citation always resolves. The data is CC BY 4.0 and the tooling is MIT.
Use the identifiers as the shared reference for the field, the way a CVE number works. That is the whole point of a registry.
How this maps to the standards.
Several standards now cover AI agents. If your organization follows one, here is how this registry connects to it.
- OWASP Agentic Top 10. The taxonomy used here. Every incident in this registry is indexed to it. Published in December 2025 by the OWASP Agentic Security Initiative, a non-profit foundation. Free to read.
- AIUC-1. 51 requirements across six domains, revised quarterly. Published by an AI insurance company that also sells audits against it; independent firms certify to it. Cross-referenced to MITRE ATLAS, NIST AI RMF, ISO 42001 and the EU AI Act. Free to read.
- Google SAIF. Google’s Secure AI Framework. A free self-assessment, thirteen questions.
Scope of this summary. Read in full: AIUC-1 (all six domains), the SAIF self-assessment, the OWASP Agentic Top 10 titles, and two published vendor questionnaires. Not read: the HECVAT 4 AI section, the CSA AI Controls Matrix and its AI-CAIQ, and the 2026 SIG AI domain, which are spreadsheet downloads or licensed. Corrections through CONTRIBUTING.md.
Read the registry.
The full database, the taxonomy, the governance model, and the test that runs every published check all live in the open.