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
2022
Findings flagged
757
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
83
Claude Code
Anthropic
Partner Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:1 M:2 I:80
Prompt Safety
Top finding ████████████████████████████████████ — classified
20/26 prioritized files · b67fa4f
General Open Source
78
IronClaw
Near AI
Partner Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:1 M:2 I:169
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
13 deps scanned via OSV.dev
21/158 prioritized files · 556dfd0
General Open Source
77
ZeroClaw
ZeroClaw Labs
Partner Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:1 M:2 I:38
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
26 deps scanned via OSV.dev
44/47 prioritized files · a1b641e
General Open Source
74
OpenClaw
OpenClaw Labs
Partner Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:2 I:2
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
61 deps scanned via OSV.dev
60/16210 prioritized files · 688777c
General Open Source
74
UI-TARS
ByteDance
Partner Preliminary scan Jun 4, 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 4, 2026 Static refresh · AI findings preserved
H:2 M:2 I:1
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
60/2491 prioritized files · 34af59c
General Open Source
72
PicoClaw
Sipeed
Partner Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:2 I:5
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
50 deps scanned via OSV.dev
60/64 prioritized files · 0ce6e20
Multi-Agent Open Source
71
LangGraph
LangChain Inc.
Node Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:2 I:6
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
20 deps scanned via OSV.dev
60/460 prioritized files · 43682f0
Multi-Agent Open Source
70
CrewAI
CrewAI Inc.
Node Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:2 I:40
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
60/1210 prioritized files · aed6923
General Open Source
70
PydanticAI
Pydantic
Node Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:3 I:6
Loop SafetyPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
6 deps scanned via OSV.dev
49/609 prioritized files · 60f5147
Multi-Agent Open Source
69
AutoGen
Microsoft Research
Node Preliminary scan Jun 4, 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
Research Open Source
65
Dexter
virattt
Node Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:5 I:12 CVE:3
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
35 deps scanned via OSV.dev
60/185 prioritized files · 8d94198
General Open Source
63
Moltis
Moltis Org
Node Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
M:12 I:27 CVE:10
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
23 deps scanned via OSV.dev
60/272 prioritized files · d87c542
Multi-Agent Open Source
62
OpenAI Swarm
OpenAI
Node Preliminary scan Jun 4, 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
General Open Source
57
LlamaIndex
LlamaIndex Inc.
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:1 M:12 I:2 CVE:10
Dependency VulnerabilityTool Abuse Risk
Top finding ████████████████████████████████████ — classified
17 deps scanned via OSV.dev
60/3958 prioritized files · 9aa5ee5
General Open Source
56
Semantic Kernel
Microsoft
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:82 I:11 CVE:81
Loop SafetyDependency VulnerabilityPrompt Safety
Top finding ████████████████████████████████████ — classified
34 deps scanned via OSV.dev
60/1266 prioritized files · 417d62f
General Open Source
56
UI-TARS Desktop
ByteDance
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:150 I:63 CVE:148
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
376 deps scanned via OSV.dev
60/1252 prioritized files · e9f3387
Multi-Agent Open Source
55
Paperclip
PaperclipAI
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:22 I:35 CVE:20
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
101 deps scanned via OSV.dev
60/1502 prioritized files · d60f50e
General Open Source
55
OpenFang
RightNow AI
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:12 I:392 CVE:10
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
9 deps scanned via OSV.dev
36/39 prioritized files · acf2587
General Open Source
53
Mastra
Mastra AI
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:68 I:54 CVE:66
Dependency VulnerabilityTool Abuse RiskPrompt Safety
Top finding ████████████████████████████████████ — classified
196 deps scanned via OSV.dev
60/5924 prioritized files · acc7741
General Open Source
52
Hermes Agent
NousResearch
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:19 I:18 CVE:17
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
163 deps scanned via OSV.dev
34/2591 prioritized files · ee7948e
General Open Source
51
AutoGPT
Significant Gravitas
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:13 I:21 CVE:11
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
150 deps scanned via OSV.dev
20/1863 prioritized files · 2ca389e
General Open Source
50
Agno
Agno (ex-Phidata)
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:3 M:131 I:3 CVE:129
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
351 deps scanned via OSV.dev
60/3928 prioritized files · a2f800d
General Open Source
50
Cherry Studio
CherryHQ
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:3 M:63 I:10 CVE:61
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
440 deps scanned via OSV.dev
60/2491 prioritized files · 5706307
General Open Source
48
Nanobot
HKUDS
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:2 M:19 I:29 CVE:17
Loop SafetyDependency VulnerabilityTool Abuse RiskPrompt Safety
Top finding ████████████████████████████████████ — classified
50 deps scanned via OSV.dev
34/432 prioritized files · c77ca16
Multi-Agent Open Source
47
MetaGPT
FoundationAgents
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:3 M:57 I:12 CVE:55
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 4, 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
59/304 prioritized files · e310ae5
Code Open Source
46
OpenHands
All Hands AI
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:3 M:15 I:10 CVE:11
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
98 deps scanned via OSV.dev
60/1313 prioritized files · 904e9cf
General Open Source
45
Strands Agents
AWS / Strands
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:3 M:13 I:24 CVE:9
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
110 deps scanned via OSV.dev
60/1019 prioritized files · 0e0035f
General Open Source
44
smolagents
Hugging Face
Rejected Preliminary scan Jun 4, 2026 Static refresh · AI findings preserved
H:3 M:82 I:34 CVE:77
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████ — classified
26 deps scanned via OSV.dev
27/77 prioritized files · e8b988d

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.

Apply for Access