0
Initializing Crucible
Open Source · Agent Security · OWASP Top 10

BREAK.
BEFORE
THEY DO

Crucible stress-tests AI agents against every known attack vector — prompt injection, goal hijacking, tool misuse — before your system reaches production.

View on GitHub Explore Modules →
Scroll to explore
Prompt Injection
Goal Hijacking
Tool Misuse
OWASP Agentic 2026
MCP Security
Multi-Agent Hardening
Red Teaming
CI/CD Integration
LangChain · CrewAI · AutoGen
Apache 2.0
Open Source
Prompt Injection
Goal Hijacking
Tool Misuse
OWASP Agentic 2026
MCP Security
Multi-Agent Hardening
Red Teaming
CI/CD Integration
LangChain · CrewAI · AutoGen
Apache 2.0
Open Source
Prompt Injection
Goal Hijacking
Tool Misuse
OWASP Agentic 2026
MCP Security
Multi-Agent Hardening
Red Teaming
CI/CD Integration
LangChain · CrewAI · AutoGen
Apache 2.0
Open Source
Prompt Injection
Goal Hijacking
Tool Misuse
OWASP Agentic 2026
MCP Security
Multi-Agent Hardening
Red Teaming
CI/CD Integration
LangChain · CrewAI · AutoGen
Apache 2.0
Open Source
The Problem

AI Agents
Ship
Untested

83% of organizations are deploying AI agents in 2026. Only 29% feel ready to do it securely. The gap between deployment speed and security maturity is where breaches happen.

The Attack Surface

1000+
Known
Vectors

Every AI agent exposes a new attack surface. OWASP published the Agentic Top 10 in December 2025 — the first formal taxonomy of autonomous AI risks. Crucible covers all of them.

The Solution

Test
Before
Deploy

Crucible runs 1,000+ adversarial attack scenarios against your agent in under 60 seconds. Automated, continuous, and integrated into your CI/CD pipeline.

01
What Crucible Tests

Eight Modules.
Zero Blind Spots.

Every attack surface an AI agent exposes — covered, tested, and scored before you ship.

01 / 08
Reliability Testing
Runs your agent 10× on identical inputs. Scores variance and detects non-deterministic failure modes.
Live v0.1
02 / 08
OWASP Top 10
Full coverage of all 10 OWASP Agentic AI risks. Goal hijacking, tool misuse, identity abuse, memory poisoning.
Live v0.1
03 / 08
Hallucination Detection
Benchmarks responses against ground truth. Scores factual accuracy and identifies hallucination patterns.
Live v0.1
04 / 08
Goal Completion
Did the agent actually finish the task? Evaluates outcomes, not just output format or response length.
v0.2
05 / 08
Tool Use Accuracy
Verifies agents call correct tools with valid parameters. Detects tool abuse and unauthorized API access.
v0.2
06 / 08
Multi-Agent Handoffs
Tests context integrity across agent-to-agent comms. Detects context poisoning in multi-step pipelines.
v0.3
07 / 08
Cost Efficiency
Token usage, latency, cost-per-task scoring. Production readiness report with optimization guidance.
v0.3
08 / 08
CI/CD Integration
GitHub Actions plugin. Fails your build automatically if agent security score drops below threshold.
v0.4
Live Simulation

The Crucible
In Action.

Witness a real-time adversarial scan. 1,247 vectors deployed. Zero blind spots remaining.

CRUCIBLE_ENGINE_V1.0.4 - ACTIVE_SCAN
● RECORDING
[ 16:34:53 ] CRUCIBLE CORE INITIALIZED
[ 16:34:54 ] CONNECTING TO TARGET: https://agent-v4.nexus-ai.io
[ 16:34:55 ] READY FOR DEPLOYMENT...
--------------------------------------------------
SCANNING...
PROGRESS: 0%
Three Steps

Install.
Configure.
Run.

01
Step 01
Install in One Line
One pip install, zero dependencies hell. Works on Python 3.10+. No Docker, no cloud signup, no API keys to start.
$ pip install crucible-security
✓ Installed crucible-security 0.1.0
02
Step 02
Point at Your Agent
Define your agent endpoint and attack scope. Choose modules, set thresholds, configure reporting — or use smart defaults.
# crucible.yaml
target: https://my-agent.io
modules: [security, reliability]
threshold: 80
03
Step 03
Get Your Score
Crucible hammers your agent with 1,000+ adversarial scenarios. You get a detailed report with severity, reproduction steps, and fix suggestions.
$ crucible scan
⠸ Running 1,247 attack vectors...
COMPLETE — Score: 74/100
3 critical · 7 medium · 12 low
"Every AI agent is a
new attack surface.
We exist to find the cracks
before production does."
— The Crucible Team · Open Source · Built in 2026
Apache 2.0 License

Fully
Open Source.
Forever.

Crucible's core is and always will be free. No paywalls, no telemetry, no lock-in. Built by the community, for the community building AI.

crucible — terminal
$ pip install crucible-security
✓ Installed crucible-security 0.1.0
 
$ crucible scan --target https://my-agent.com
⠸ Loading attack modules...
✓ Security: 1,247 vectors loaded
✓ Reliability module ready
✓ Hallucination module ready
⠸ Running adversarial scan...
 
SCAN COMPLETE — Score: 74/100
3 critical · 7 medium · 12 low
→ ./crucible-report.json saved
$
The Team

Built by Builders.
Open to Builders.

We recruit through contribution. Your code speaks louder than your resume. Contribute — and we'll reach out.

Founder & Core
Khalid Saifullah Sayyed
AI & backend engineer. LLM security specialist. IIT Patna hackathon winner. Contributor to YC W20 10k★ repos. Building the future of AI agent security.
LLM SecurityMulti-AgentFastAPIRed TeamingPython
Open Position
AI / LLM Engineer
Deep understanding of language model internals. Can build adversarial prompt systems that find vulnerabilities others miss. Transformer architecture knowledge essential.
TransformersAdversarial MLLangChainPrompt Eng
Open Position
Security Engineer
Traditional security background meets AI. Deep OWASP knowledge, penetration testing experience, now applying it to agentic systems.
PentestingOWASPCVE ResearchThreat Modeling
Open Position
Backend / Infra
Builds systems running thousands of concurrent attack simulations. Async Python, job queues, cloud-native. Performance matters.
FastAPIRedisDockerCeleryGo
Open Position
Frontend / DX
Builds the dashboard, CLI UX, and docs. Believes developer experience is a product decision. Obsessed with making complex things feel simple.
ReactTypeScriptCLI DesignDocs
+
Could Be You
Contribute to the repo. If your work stands out, we find you.
Contribute Now
Get Started Now

YOUR
AGENT
IS NOT
SAFE. YET.

Every day you ship an untested AI agent, you leave a door open. Crucible runs in 60 seconds. It's free. There is no reason to wait.

Star on GitHub — It's Free Read Docs →