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
2899
Findings flagged
1794
CVEs detected
Static analysis + OSV.dev CVE scan + NVIDIA Llama 70B audit · Questions? [email protected]
Tiers
Sovereign ≥85
Partner ≥75
Node ≥60
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 Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:3 I:1
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
60/1368 prioritized files · 772c6be
General Open Source
78
UI-TARS
ByteDance
Partner Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:2 I:6
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
4/5 prioritized files · 582f3a7
General Open Source
76
LangChain Agent
LangChain Inc.
Partner Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:2 I:2
Prompt Safety
Top finding ████████████████████████████████████, classified
60/2639 prioritized files · d670a3a
Multi-Agent Open Source
76
LangGraph
LangChain Inc.
Partner Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:2 I:5
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
20 deps scanned via OSV.dev
60/491 prioritized files · 1400d25
General Open Source
76
ZeroClaw
ZeroClaw Labs
Partner Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:2 I:91
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
30 deps scanned via OSV.dev
40/148 prioritized files · e8d2e5f
General Open Source
73
Moltis
Moltis Org
Node Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:3 I:30
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
23 deps scanned via OSV.dev
60/297 prioritized files · b75046a
General Open Source
72
PicoClaw
Sipeed
Node Preliminary scan Oct 19, 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 · bbf6893
Multi-Agent Open Source
71
CrewAI
CrewAI Inc.
Node Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:3 I:40
Prompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
60/1433 prioritized files · c6e500a
General Open Source
69
OpenClaw
OpenClaw Labs
Node Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:4 I:2 CVE:2
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
72 deps scanned via OSV.dev
60/47268 prioritized files · e559b9e
General Open Source
69
IronClaw
Near AI
Node Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:5 I:11 CVE:3
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
49 deps scanned via OSV.dev
53/607 prioritized files · b0b999d
Multi-Agent Open Source
64
AutoGen
Microsoft Research
Node Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:6 I:9 CVE:4
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
38 deps scanned via OSV.dev
60/593 prioritized files · 004749e
Multi-Agent Open Source
62
OpenAI Swarm
OpenAI
Node Preliminary scan Oct 19, 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
60
Agno
Agno (ex-Phidata)
Node Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:583 I:1 CVE:581
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
345 deps scanned via OSV.dev
60/5384 prioritized files · 643f6e7
Code Open Source
60
OpenHands
All Hands AI
Node Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:19 I:25 CVE:17
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
101 deps scanned via OSV.dev
55/1177 prioritized files · 8d39305
General Open Source
60
UI-TARS Desktop
ByteDance
Node Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:241 I:63 CVE:239
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
377 deps scanned via OSV.dev
60/1264 prioritized files · 3ac2cb8
General Open Source
56
LlamaIndex
LlamaIndex Inc.
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:156 I:1 CVE:153
Dependency VulnerabilityTool Abuse Risk
Top finding ████████████████████████████████████, classified
217 deps scanned via OSV.dev
60/3886 prioritized files · 619d746
General Open Source
56
Semantic Kernel
Microsoft
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:97 I:11 CVE:96
Loop SafetyDependency VulnerabilityPrompt Safety
Top finding ████████████████████████████████████, classified
33 deps scanned via OSV.dev
60/1278 prioritized files · 7a92cd4
General Open Source
56
Hermes Agent
NousResearch
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:21 I:11 CVE:19
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
175 deps scanned via OSV.dev
50/13350 prioritized files · cc6b1f2
General Open Source
55
AutoGPT
Significant Gravitas
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:24 I:24 CVE:22
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
144 deps scanned via OSV.dev
22/4108 prioritized files · 8d4a965
General Open Source
55
OpenFang
RightNow AI
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:23 I:392 CVE:21
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
9 deps scanned via OSV.dev
36/39 prioritized files · acf2587
General Open Source
54
Mastra
Mastra AI
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:16 I:54 CVE:14
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
174 deps scanned via OSV.dev
60/13504 prioritized files · 203fec1
Multi-Agent Open Source
54
Paperclip
PaperclipAI
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:20 I:46 CVE:17
Dependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
167 deps scanned via OSV.dev
60/6050 prioritized files · 7ec6e1a
General Open Source
53
PydanticAI
Pydantic
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:2 M:31 I:4 CVE:28
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
10 deps scanned via OSV.dev
37/1985 prioritized files · 82e8709
Multi-Agent Open Source
53
Agency Swarm
VRSEN
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:1 M:34 I:12 CVE:32
Dependency VulnerabilityTool Abuse Risk
Top finding ████████████████████████████████████, classified
22 deps scanned via OSV.dev
60/435 prioritized files · a86d657
General Open Source
50
Cherry Studio
CherryHQ
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:3 M:103 I:16 CVE:101
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
463 deps scanned via OSV.dev
44/5814 prioritized files · 5967cf3
Research Open Source
49
Dexter
virattt
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:3 M:29 I:12 CVE:27
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
35 deps scanned via OSV.dev
60/218 prioritized files · 534f6be
General Open Source
48
smolagents
Hugging Face
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:3 M:216 I:35 CVE:214
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
26 deps scanned via OSV.dev
27/77 prioritized files · 96f33fa
General Open Source
47
Strands Agents
AWS / Strands
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:3 M:14 I:37 CVE:11
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
162 deps scanned via OSV.dev
60/2025 prioritized files · 3bd98e6
Multi-Agent Open Source
47
MetaGPT
FoundationAgents
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:3 M:172 I:13 CVE:170
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
97 deps scanned via OSV.dev
60/919 prioritized files · 11cdf46
General Open Source
45
Nanobot
HKUDS
Rejected Preliminary scan Oct 19, 2026 Static refresh · AI findings preserved
H:4 M:25 I:18 CVE:23
Loop SafetyDependency VulnerabilityPrompt SafetyTool Abuse Risk
Top finding ████████████████████████████████████, classified
66 deps scanned via OSV.dev
32/1231 prioritized files · 909b277

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