Search
@stroq/cli
agybay_07
Local action firewall for AI agents: scans what the agent reads, taints the session, blocks dangerous follow-up actions
bash-vet-mcp
MCP server that vets LLM-emitted shell commands BEFORE execution. Detects rm -rf in chains, package-glob removal, dd/mkfs/wipefs, chmod 777, curl|bash, chained shutdown, git destructive ops. 24 rules / 8 families. Sub-second, local, no API key. Defensive complement to MCPShell/mcp-shell/mcp-bash.
...more@csgaglobal/frontier-model-governance
csga_global
AI governance for frontier AI models, foundation models, and general-purpose AI systems. Covers systemic risk assessment, model evaluation, and frontier AI safety obligations under EU AI Act and international frameworks.
...more@stylusnexus/agentarmor-ml
stylusnexus
ML classifier add-on for Agent Armor. Downloads and runs a DeBERTa-v3-small ONNX model for agent trap detection.
acrf-mcp-scan
Ravi Karthick Sankara Narayanan, Kanna Sekar
MCP server inventory and risk scanner. Implements ACRF-03 defense pattern.
giskard
Giskard AI <[email protected]>
The testing framework dedicated to ML models, from tabular to LLMs
CyberScanAI
medbenali
AI Agent Tool for Penetration Testing and Network Forensics
toolgovern-integration-oma
rudrendu_paul_packages
Adapter shapes (per-tool governedTool and dispatcher-style governedExecutor) for wiring toolgovern into an open-multi-agent-style tool-executor call site.
...morefc-security
sherwyn
fc security
Kali Pentest
x-glacier
AI agent skill for autonomous penetration testing via Kali Linux — 199 CLI tools, 15 scenario playbooks, depth-enforced workflows over SSH or Docker. Works with Claude Code, OpenClaw, and Hermes Agent.
...morePalimpsest
JINGQINLIN
Palimpsest is an LLM-assisted semantic code enhancement framework that bridges Ghidra decompilation and CodeQL database construction. It is optimized for IoT device firmware analysis and for generating CodeQL-buildable source code.
...moretokenbreak-scanner
TokenBreak Scanner Contributors
Detect TokenBreak adversarial vulnerabilities in LLMs, classifiers, and encoders. Audit HuggingFace tokenizer artifacts for BPE/WordPiece attack surface.
...morePriestsBasilisk
the-priest
Open-source autonomous AI pentester that proves every exploit — 87/113 on OWASP Juice Shop, black-box, on a budget model and a flawless 22 of 22 on Escape's Duck Store API — fully autonomous, black-box, outscoring Cascade and a bare Claude Opus 4.8 on the very same board, all while running on one of the cheapest models on the market.
...morekoma-gate
kotarokielo
Semantic request filtering and scope control for AI apps.
@xshieldai/chitta-detect
rocketlang
Memory poisoning detection primitives for AI agents — pure pattern matchers (RAG trust, agent-role imperatives, tool-output poisoning, capability expansion, injection fingerprints) + opt-in Agentic Control Center event bus. Extracted from chitta-guard.
...moreSecGPT
llm-platform-security
An Execution Isolation Architecture for LLM-Based Agentic Systems
react-native-ec-encryption
heawen110
A hardware-backed encryption and decryption library for React Native
dssrf
relunsec
SSRF defense library for Node.js with safe URL validation utilities.
shipgrade
Jacob Dennis
Grade your LLM feature before you ship: a plain-English, severity-ranked A-to-F safety and regulated-domain compliance report card.
...more@soterai/vercel-ai-sdk-middleware
yashchauhan66
Soter is a safety layer for AI chatbots, agents, RAG systems, and LLM applications.