Cyber Security for Startups & New Founders -- Protect your business from day one69 OWASP Agentic AI violations detected across 39 major frameworks. Static analysis against 12 detection rules mapped to OWASP Agentic Top 10, MITRE ATT&CK, and STRIDE threat models.
Cyber Security for Startups & New Founders -- Protect your business from day one
Tamper-proof content protection for creators -- Watermark, sign, and verify your workZero trust identity and MCP authentication for AI agents
| Framework | Category | Stars | Verdict | Risk | OWASP | ATT&CK | STRIDE | Findings | Scanned |
|---|---|---|---|---|---|---|---|---|---|
| AutoGPT | Autonomous Agent | 182K+ | ✗ FAIL | 65 | AA-03 AA-09 | T1059 T1610 | EoP | exec(), os.system(), no sandbox | 2026-03-10 |
| BabyAGI | Autonomous Agent | 20K+ | ✗ FAIL | 55 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | exec(), eval(), supply chain | 2026-03-10 |
| Open Interpreter | Code Agent | 57K+ | ✗ FAIL | 80 | AA-03 AA-09 AA-01 | T1059 T1610 T1548 | EoP | exec(), os.system(), child_process, no sandbox | 2026-03-10 |
| MetaGPT | Multi-Agent | 48K+ | ✗ FAIL | 50 | AA-03 AA-09 | T1059 T1610 | EoP | subprocess shell=True, no sandbox | 2026-03-10 |
| GPT Engineer | Code Agent | 53K+ | ✗ FAIL | 55 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | exec(), subprocess, supply chain | 2026-03-10 |
| ChatDev | Multi-Agent | 27K+ | ✗ FAIL | 50 | AA-03 AA-09 | T1059 T1610 | EoP | exec(), subprocess | 2026-03-10 |
| SuperAGI | Autonomous Agent | 15K+ | ✗ FAIL | 50 | AA-03 AA-01 | T1059 T1548 | EoP | subprocess shell=True, excessive agency | 2026-03-10 |
| CAMEL | Multi-Agent | 6K+ | ✗ FAIL | 40 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | eval(), supply chain | 2026-03-10 |
| AgentGPT | Autonomous Agent | 32K+ | ✗ FAIL | 55 | AA-03 AA-09 AA-06 | T1059 T1610 T1195 | EoP Tamper | eval(), no sandbox, supply chain | 2026-03-10 |
| LangChain | Agent Framework | 100K+ | ~ WARN | 26 | AA-06 AA-02 | T1195 T1190 | Tamper | Supply chain, prompt injection vectors | 2026-03-10 |
| CrewAI | Multi-Agent | 45K+ | ~ WARN | 23 | AA-06 AA-04 | T1195 T1078 | Tamper EoP | Supply chain, excessive permissions | 2026-03-10 |
| Microsoft AutoGen | Multi-Agent | 50K+ | ~ WARN | 23 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | Code execution patterns, supply chain | 2026-03-10 |
| Semantic Kernel | Agent Framework | 23K+ | ~ WARN | 18 | AA-06 AA-07 | T1195 T1059.007 | Tamper | Supply chain, output handling | 2026-03-10 |
| TaskWeaver | Code Agent | 5K+ | ~ WARN | 23 | AA-03 AA-09 | T1059 T1610 | EoP | Eval patterns, no sandbox | 2026-03-10 |
| OpenAI Agents SDK | Agent Framework | 19K+ | ~ WARN | 11 | AA-06 AA-01 | T1195 T1548 | Tamper EoP | Supply chain, excessive agency config | 2026-03-10 |
| Haystack | Agent Framework | 18K+ | ~ WARN | 11 | AA-06 AA-07 | T1195 T1059.007 | Tamper | Supply chain, output handling | 2026-03-10 |
| Smolagents | Agent Framework | 15K+ | ~ WARN | 18 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | Code execution, supply chain | 2026-03-10 |
| Swarm | Multi-Agent | 18K+ | ~ WARN | 11 | AA-01 AA-06 | T1548 T1195 | EoP Tamper | Excessive agency, supply chain | 2026-03-10 |
| Google ADK | Agent Framework | 15K+ | ✓ PASS | 3 | AA-06 | T1195 | Tamper | Minor supply chain note | 2026-03-10 |
| Anthropic Claude SDK | SDK | 8K+ | ✓ PASS | 0 | -- | -- | -- | No issues detected | 2026-03-10 |
| Vercel AI SDK | SDK | 12K+ | ✓ PASS | 0 | -- | -- | -- | No issues detected | 2026-03-10 |
| LlamaIndex | Agent Framework | 38K+ | ✓ PASS | 3 | AA-06 | T1195 | Tamper | Minor supply chain note | 2026-03-10 |
| Phidata | Agent Framework | 18K+ | ✓ PASS | 0 | -- | -- | -- | No issues detected | 2026-03-10 |
| Instructor | SDK | 9K+ | ✓ PASS | 0 | -- | -- | -- | No issues detected | 2026-03-10 |
| Mastra | Agent Framework | 10K+ | ✓ PASS | 0 | -- | -- | -- | No issues detected | 2026-03-10 |
| Amazon Bedrock Agents | Cloud Agent | N/A | ✓ PASS | 3 | AA-06 | T1195 | Tamper | Minor supply chain note | 2026-03-10 |
| AgentSign SDK | Identity SDK | OSS | ✓ PASS | 0 | -- | -- | -- | No issues detected | 2026-03-10 |
| n8n | Workflow Agent | 178K+ | ~ WARN | 26 | AA-03 AA-09 | T1059 T1610 | EoP | Code execution nodes, shell command node, spawn() | 2026-03-13 |
| Langflow | Agent Builder | 145K+ | ~ WARN | 23 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | Inherits LangChain exec patterns, code nodes | 2026-03-13 |
| Dify | Agent Platform | 132K+ | ~ WARN | 21 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | Sandboxed code exec, tool calling, subprocess | 2026-03-13 |
| Browser Use | Browser Agent | 80K+ | ✗ FAIL | 60 | AA-03 AA-09 AA-01 | T1059 T1610 T1548 | EoP | Arbitrary browser control, JS injection, no sandbox | 2026-03-13 |
| OpenHands | Code Agent | 69K+ | ✗ FAIL | 70 | AA-03 AA-09 AA-01 | T1059 T1610 T1548 | EoP | subprocess, exec, shell commands, file write | 2026-03-13 |
| Crawl4AI | Web Agent | 61K+ | ~ WARN | 21 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | Playwright subprocess, arbitrary URL fetch | 2026-03-13 |
| Aider | Code Agent | 41K+ | ~ WARN | 23 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | subprocess for git/tests, shell execution | 2026-03-13 |
| Goose | Code Agent | 32K+ | ✗ FAIL | 65 | AA-03 AA-09 AA-01 | T1059 T1610 T1548 | EoP | Shell exec core, pkg install, file write, no sandbox | 2026-03-13 |
| Composio | Agent Tooling | 27K+ | ~ WARN | 18 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | Sandboxed exec, shell tools, API calls | 2026-03-13 |
| Letta | Stateful Agent | 21K+ | ~ WARN | 18 | AA-03 AA-06 | T1059 T1195 | EoP Tamper | Tool execution, subprocess, database ops | 2026-03-13 |
| Devika | Code Agent | 19K+ | ✗ FAIL | 65 | AA-03 AA-09 AA-01 | T1059 T1610 T1548 | EoP | exec(), subprocess, browser auto, shell commands | 2026-03-13 |
| SWE-agent | Code Agent | 18K+ | ~ WARN | 26 | AA-03 AA-09 | T1059 T1610 | EoP | Docker exec, subprocess, shell commands | 2026-03-13 |
The AgentSign Registry performs automated static analysis of publicly available open-source code. All scanned projects are sourced from public GitHub repositories under their respective open-source licences. This is the same approach used by established security scanning services such as Snyk, Sonatype OSS Index, and the GitHub Advisory Database.
What we scan for: Code patterns mapped to the OWASP Agentic AI Top 10 (2025) and OWASP MCP Top 10. These are industry-standard security benchmarks, not proprietary criteria.
Fair use and responsible disclosure: This registry is published in good faith for the purpose of improving agentic AI security. If you are a maintainer of a listed project and believe a finding is inaccurate or wish to discuss remediation, please contact contact@agentsign.dev. We will promptly review and update any disputed findings.
AgentSign Registry is provided "as is" without warranty. CyberSecAI Ltd accepts no liability for decisions made based on registry data. All trademarks and project names are the property of their respective owners.
Create .github/workflows/agentsign.yml in your repo:
# .github/workflows/agentsign.yml
name: AgentSign Security Scan
on: [push, pull_request]
jobs:
scan:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: razashariff/agentsign-action@v1
with:
path: '.'
fail-on: 'FAIL'
Every push and PR gets scanned against 12 OWASP rules. FAIL blocks the merge.
Show your security status. Copy this line:
Replace YOUR-AGENT-NAME with your agent name. PASS = green, WARN = yellow, FAIL = red.
POST your code directly. No auth needed:
curl -X POST https://registry.agentsign.dev/api/scan \
-H "Content-Type: application/json" \
-d '{"code": "YOUR_CODE_HERE", "name": "my-agent"}'
Returns verdict, risk score, and findings mapped to OWASP Agentic AI Top 10.
shields.io-compatible badge. PASS = green, WARN = yellow, FAIL = red. Cached 5 minutes.
curl https://registry.agentsign.dev/api/badge/autogpt
{ "schemaVersion": 1, "label": "AgentSign", "message": "FAIL", "color": "red" }
Scan agent code against 12 OWASP rules. Max 50KB.
curl -X POST https://registry.agentsign.dev/api/scan \
-H "Content-Type: application/json" \
-d '{"code": "exec(user_input)", "name": "my-agent"}'
{ "verdict": "FAIL", "risk_score": 40, "findings": [...] }
Current rules version and count.
{ "version": "1.1.0", "rule_count": 12 }
Full registry as JSON. All 39 frameworks with verdicts and scores.
The registry scans. The platform secures. Three API calls to zero trust.