KYA™ · Know Your Agent

Agent Trust Registry

Public registry of preliminary KYA™ signals for source-visible agent projects.
Scores support due diligence and capability controls. They are not final security certifications.

30
Agents tracked
30
Preliminary scans
2195
Findings flagged
923
CVEs detected
Static analysis + OSV.dev CVE scan + NVIDIA Llama 70B audit · Questions? [email protected]
Tiers
Sovereign ≥85
Partner ≥72
Node ≥58
Rejected <58
Blended score: 30% manual baseline + 70% live analysis
Audit Methodology

How we score agents

Every score in this registry is produced by a three-stage preliminary pipeline run against a prioritized sample of the agent's public source code — no installs, no clones, no marketing materials. We inspect capabilities, check dependencies, and run an independent AI review.

Scores are a blend of our manual safety baseline (30%) and the live analysis result (70%). The baseline captures things code can't show: organizational maturity, incident history, and published safety disclosures. The live analysis reflects what's actually in the codebase today.

On false positives. Static analysis is inherently noisy. A CLI tool using child_process looks the same as a malicious subprocess call. An agent that legitimately browses the web will flag network patterns. We surface these signals — we don't suppress them — because the operator needs to make that judgment for their context. Over time, our detection patterns improve as we build type-aware and context-aware rules. Treat scores as a starting point for due diligence, not a final verdict.

01

Static code analysis

Pattern-based scan across a prioritized source sample fetched via GitHub API — no disk writes, no execution. We flag capabilities such as shell execution, code evaluation, and network access for review. A capability signal is not, by itself, a confirmed vulnerability.

02

Dependency CVE scan

We parse package.json and requirements.txt files without installing anything. Each dependency is queried against OSV.dev — Google's open vulnerability database — using their batch API. CVSS ≥7.0 is flagged as High, 4.0–7.0 as Medium. We also flag unpinned version ranges (^, ~, *) as supply chain risk.

03

AI-powered semantic audit

Source files are passed to a large language model (Llama 3.1 70B via NVIDIA NIM) with a structured security prompt. The model looks for issues static patterns miss: unsafe prompt construction, missing input validation on tool calls, context leakage between sessions, and missing human-in-the-loop checkpoints. This stage catches behavioral risks, not just syntactic ones.

04

Score composition

Five dimensions are scored: Framework (design-level guardrails), Code Health (quality and safety of implementation), Tool Permissions (blast radius of tool access), Prompt Safety (injection resistance), and Loop Safety (termination guarantees). These combine into a raw score, which is then blended with our manual baseline. Scores are re-run periodically as frameworks evolve.

Code Source Available
79
Claude Code
Anthropic
Partner Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:2 I:79
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
20/26 prioritized files · 5c1517a
General Open Source
74
OpenClaw
OpenClaw Labs
Partner Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:2 I:2
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
54 deps scanned via OSV.dev
60/16821 prioritized files · f163d77
General Open Source
74
UI-TARS
ByteDance
Partner Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:2 I:5
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
4/5 prioritized files · 582f3a7
General Open Source
73
LangChain Agent
LangChain Inc.
Partner Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:2 I:1
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
60/2534 prioritized files · 57c83d4
General Open Source
73
ZeroClaw
ZeroClaw Labs
Partner Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:2 I:44
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
26 deps scanned via OSV.dev
53/56 prioritized files · c8c2921
Multi-Agent Open Source
72
LangGraph
LangChain Inc.
Partner Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:2 I:5
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
20 deps scanned via OSV.dev
60/462 prioritized files · 8c9d59c
General Open Source
72
PicoClaw
Sipeed
Partner Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:2 I:6
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
50 deps scanned via OSV.dev
60/64 prioritized files · a75b3d1
Multi-Agent Open Source
70
CrewAI
CrewAI Inc.
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:2 I:40
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
60/1259 prioritized files · 5827abb
General Open Source
70
PydanticAI
Pydantic
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:3 I:4
Loop SafetyPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
6 deps scanned via OSV.dev
55/553 prioritized files · a84f2b3
Multi-Agent Open Source
69
AutoGen
Microsoft Research
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:3 I:9 CVE:1
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
38 deps scanned via OSV.dev
60/593 prioritized files · 027ecf0
General Open Source
63
Moltis
Moltis Org
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
M:16 I:27 CVE:14
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
23 deps scanned via OSV.dev
60/272 prioritized files · 48c9a41
Multi-Agent Open Source
62
OpenAI Swarm
OpenAI
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:4 M:3 I:5
Loop SafetyPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
55/63 prioritized files · 6af0b4c
Research Open Source
62
Dexter
virattt
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:7 I:12 CVE:5
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
35 deps scanned via OSV.dev
60/190 prioritized files · c5cb794
General Open Source
60
UI-TARS Desktop
ByteDance
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:1 M:164 I:63 CVE:162
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
376 deps scanned via OSV.dev
60/1252 prioritized files · e9f3387
General Open Source
60
IronClaw
Near AI
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:1 M:12 I:168 CVE:10
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
20 deps scanned via OSV.dev
25/419 prioritized files · 35b7f50
General Open Source
60
Cherry Studio
CherryHQ
Node Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:1 M:79 I:9 CVE:77
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
416 deps scanned via OSV.dev
60/2897 prioritized files · 1cacacb
General Open Source
57
Mastra
Mastra AI
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:1 M:82 I:54 CVE:80
Dependency VulnerabilityTool Abuse Risk
Top finding ████████████████████████████████████ — classified
174 deps scanned via OSV.dev
60/6623 prioritized files · 095c206
General Open Source
56
LlamaIndex
LlamaIndex Inc.
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:1 M:13 I:1 CVE:10
Dependency VulnerabilityTool Abuse Risk
Top finding ████████████████████████████████████ — classified
17 deps scanned via OSV.dev
60/3948 prioritized files · 9f66e8a
General Open Source
56
Hermes Agent
NousResearch
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:1 M:22 I:26 CVE:20
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
164 deps scanned via OSV.dev
36/3166 prioritized files · 9259d1e
Multi-Agent Open Source
55
Paperclip
PaperclipAI
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:26 I:39 CVE:24
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
101 deps scanned via OSV.dev
60/1739 prioritized files · 51ffbb3
General Open Source
55
OpenFang
RightNow AI
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:14 I:392 CVE:12
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
9 deps scanned via OSV.dev
36/39 prioritized files · acf2587
General Open Source
54
Semantic Kernel
Microsoft
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:94 I:11 CVE:92
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
36 deps scanned via OSV.dev
60/1268 prioritized files · 82f2442
General Open Source
54
Agno
Agno (ex-Phidata)
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:197 I:3 CVE:195
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
350 deps scanned via OSV.dev
60/4035 prioritized files · c581db4
General Open Source
52
AutoGPT
Significant Gravitas
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:13 I:20 CVE:11
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
151 deps scanned via OSV.dev
20/2049 prioritized files · 150514f
General Open Source
50
smolagents
Hugging Face
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:94 I:35 CVE:91
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
26 deps scanned via OSV.dev
27/77 prioritized files · 526069c
Code Open Source
48
OpenHands
All Hands AI
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:3 M:12 I:10 CVE:8
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
96 deps scanned via OSV.dev
60/1364 prioritized files · ceef693
General Open Source
47
Strands Agents
AWS / Strands
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:4 M:7 I:24 CVE:5
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
122 deps scanned via OSV.dev
60/1199 prioritized files · 1b6f8a0
Multi-Agent Open Source
47
MetaGPT
FoundationAgents
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:3 M:66 I:12 CVE:64
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
97 deps scanned via OSV.dev
60/919 prioritized files · 11cdf46
Multi-Agent Open Source
47
Agency Swarm
VRSEN
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:2 M:23 I:12 CVE:21
Loop SafetyDependency VulnerabilityTool Abuse Risk
Top finding ████████████████████████████████████ — classified
22 deps scanned via OSV.dev
60/320 prioritized files · f6f35a2
General Open Source
41
Nanobot
HKUDS
Rejected Preliminary scan Jun 24, 2026 Static refresh · AI findings preserved
H:4 M:23 I:28 CVE:21
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
49 deps scanned via OSV.dev
32/490 prioritized files · 943191f

Apply for a KYA™ evaluation.

Approved capabilities depend on your agent, operator, jurisdiction, cohort, and licensed infrastructure partners. A preliminary registry score does not guarantee financial access.

Get Quick Sell token