OpenA2A · Threat intelligence

The attacks against AI agents, mapped and graded.

An evidence-graded kill chain for agent systems: 9 tactics, 61 techniques, 40attack classes. Each one is tied to something real: observed in the wild, reproduced in the lab, or adapted from established attacks. Built to complement MITRE ATT&CK and OWASP, not replace them.

9
Tactics
61
Techniques
40
Attack classes
132
Evidence records
22 techniques
Coverage dashboard

What the evidence says

Every technique carries an evidence grade and a source trail. These panels are computed live from the matrix at build time. Nothing here is estimated.

Evidence grade mix
61
techniques
Observed 16
Validated 42
Adapted 3
Observed in the wild · reproduced in lab · adapted from prior art.
Evidence by source
HackMyAgent123
Shodan7
AgentPwn2
Records aggregated across all techniques.
Most evidenced techniques
T-3006 · Context Window Credential Leak20
T-3003 · Tool Response Credential Capture15
T-2005 · Tool Description Injection9
T-9006 · Supply Chain Compromise9
T-6004 · Skill/Plugin Backdoor8
T-9001 · Data Manipulation8
Total evidence records per technique.
Defensive coverage
Techniques with HackMyAgent detection61/61 · 100%
Techniques with OASB mitigation61/61 · 100%

Detection maps to HackMyAgent checks; mitigation maps to OASB controls. A technique without either is a gap worth closing. See Coverage & gaps.

The matrix

Kill-chain grid

Nine stages, left to right, the way an agent compromise actually unfolds. Search, filter by evidence grade, or surface only what's active right now. Every cell links to the full technique dossier.

61 of 61 techniques
Sort
Evidence gradeObservedValidatedAdapted123evidence recordsactive threat
The standard

Nothing here is hand-waved

Every technique carries one of three evidence grades. The grade tells you exactly how much to trust it.

Observed16 techniques

Confirmed in real-world production systems, security incidents, or internet-wide exposure assessments.

Validated42 techniques

Reproduced in a controlled lab (DVAA) with documented steps and independent verification. DVAA

Adapted3 techniques

A well-understood traditional technique applied to the agent context. Not yet observed agent-specifically.

Positioning

Where this fits

Infrastructure layer

MITRE ATT&CK

Enterprise network and endpoint attacks. The layer below the agent.

Model layer

MITRE ATLAS

Adversarial ML and model-level attacks. The layer below the agent.

Agent layer

Agent Threat Matrix

Infrastructure, governance, protocols, memory, and identity: the agent layer, between model and user.