Prompt Injection Python Packages

hol-guard

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

plugin-scanner

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

llm-guard

The Security Toolkit for LLM Interactions

navi-sanitize

Deterministic input sanitization for untrusted text — invisible characters, homoglyphs, and encoding tricks, handled before your code sees them. Zero dependencies, no ML. Python 3.12+.

skylos

Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistakes before merge. For first timers refer to https://duriantaco.github.io/skylos/repo-map/

aig-skill-scan

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

agentdojo

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

mcpgawk

One gateway in front of every MCP server your agents can reach. A server that changes after you approved it is caught, the call is blocked before it runs, and nothing leaves your machine.

skilltotal

Claude Code plugin that scans a package before the agent runs npx, npm install, pip install, uvx or claude mcp add. Malicious indicators block the install. High-risk packages need your approval. The scan runs on your machine and never executes the code or calls an LLM. Every finding cites a file and line. Also a CLI, GitHub Action and MCP server.

squidbrake

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

immunity-agent

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

tenuo

Task-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privilege escalation at every delegation hop, and produce signed evidence of what was allowed or denied.

complydoc

Know your documents before they reach an LLM

skillmem

Self-improving skill memory for coding agents: learn, recall, reinforce, decay — with provenance on every memory and trust only you grant. Local SQLite, no API key, no cloud.

prismor

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

guardana-core

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

guardana-report

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

guardana-rules

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

guardana-cli

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

guardana-server

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

chock

Governance-as-code for AI coding agents: author a policy once, enforce it on every agent (Claude, Copilot, Cursor, Codex) via git hooks, CI, and native controls.

sunglasses

Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,569 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.

palisade-sec

Applied agentic-safety infrastructure: statically detects, evaluates, and gates untrusted-input → LLM → exec/shell/SQL/HTTP paths in Python and JavaScript/TypeScript AI systems. Offline, keyless, precision-first; optional bring-your-own-endpoint judgment layer.

agent-memory-guard

OWASP Foundation web repository