AI Security Matrix

A curated list of AI-enabled security testing tools.

trailofbits/fickling

Licence
LGPL
Maintainers
23 contributors · top author wrote 26%
Size
9,573 lines · 46 code files · tests, CI, lockfile
Bundled tools
none found
Shares files with
no overlap found

Before running it

Ships compiled binaries you did not build no
Asks for root or sudo no
Reads credential paths such as ~/.aws or ~/.ssh yes
Installs software on your host yes
Calls an endpoint the project does not own no
Contains long encoded blobs you cannot read yes

scanner

Last updatedCategoryToolScopeStarsFlags
★ today scanner promptfoo/promptfoo new
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
 llmagentic 25k rootcredentialsinstallscalls outopaque
★ today scanner snyk/agent-scan new
Security scanner for AI agents, MCP servers and agent skills.
 agentic 3.0k rootcredentialsinstalls
★ today scanner Tencent/AI-Infra-Guard new
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
 llmagentic 6.4k rootcredentialsinstallscalls out
★ today scanner Lab700xOrg/aisbom new
Static security scanner for ML model files — detects pickle bombs, Keras Lambda RCE and GGUF template injection, and generates CycloneDX / SPDX AI-BOMs (AIBOM) as EU AI Act, CRA and FDA §524B evidence.
 modfile 77 none
★ today scanner promptfoo/modelaudit new
Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment
 modfile 70 rootcredentialscalls out
★ 1d scanner microsoft/PyRIT new
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
 llm 4.5k rootinstallscalls outopaque
★ 1d scanner cisco-ai-defense/mcp-scanner new
Scan MCP servers for potential threats & security findings.
 agentic 1.1k rootcredentials
★ 3d scanner adithyan-ak/AgentHound new
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
 agentic 434 rootcredentialsinstalls
★ 4d scanner msoedov/agentic_security new
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
 llmagentic 2.0k calls out
★ 5d scanner trailofbits/fickling new
A Python pickling decompiler and static analyzer
 modfile 668 credentialsinstallsopaque
★ 6d scanner NVIDIA/garak new
the LLM vulnerability scanner
 llm 9.2k root
★ 14d scanner mmaitre314/picklescan new
Security scanner detecting Python Pickle files performing suspicious actions
 modfile 423 none
★ 25d scanner confident-ai/deepteam new
DeepTeam is a framework to red team LLMs and AI agents.
 llmagentic 2.8k installscalls out
209d scanner protectai/modelscan new
Protection against Model Serialization Attacks
 modfile 774 credentials
221d scanner cyberark/FuzzyAI new
A powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs.
 llm 1.6k none
268d scanner mbrg/power-pwn new
An offensive/defense security toolset for discovery, recon and ethical assessment of AI Agents
 cloudllm 1.2k root
288d scanner utkusen/promptmap new
a security scanner for custom LLM applications
 llm 1.3k none
292d scanner splx-ai/agentic-radar new
A security scanner for your LLM agentic workflows
 agentic 1.1k installs
1.2y scanner Azure/counterfit new
a CLI that provides a generic automation layer for assessing the security of ML models
 llm 938 root
1.6y scanner protectai/vulnhuntr new
Zero shot vulnerability discovery using LLMs
 code 2.8k installs