Agent Security 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.

167K 844 149

plugin-scanner

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

138K 844 149

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.

63K 7K 653

datafog

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

47K 77 15

agent-hooks-sdk

Framework-neutral control contract for AI agents: eight interception points, three verdicts, and a conformance kit.

30K 19 4

tempus-ddb

Fail-closed B2A security gate for autonomous agent actions with signed policies and verifiable receipts.

27K 2 0

vaara

Accountable Autonomy: open-source evidence layer that gates every AI agent tool call against your policy and writes a hash-chained record an auditor verifies offline, without trusting you. Root-agnostic; binds to TPM 2.0 / SEV-SNP when present. Your environment, no SaaS, no telemetry. AGPL-3.0.

22K 15 1

assurance-budget

Your AI agent says it's done. Assurance tells you what it didn't check.

17K 7 2

assurance

Your AI agent says it's done. Assurance tells you what it didn't check.

16K 7 2

assurance-cli

Your AI agent says it's done. Assurance tells you what it didn't check.

15K 7 2

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.

14K 14 15

ctrlrun

The execution safety layer for AI agents.

13K 26 1

darm-guard

Runtime authorization for AI agents: a broker executes only what a decision kernel, compiled from a machine-checked Lean 4 model, admits, and leaves signed evidence of every effect.

13K 0 0

assay-it

Open evidence profile for MCP tool actions. Enforce configured tool-call policies and record decisions and observations in offline-verifiable bundles. Optional Linux kernel controls. No hosted backend required.

12K 12 3

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.)

12K 415 55

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.

11K 103 23

assurance-mcp

Your AI agent says it's done. Assurance tells you what it didn't check.

11K 7 2

prismor

10K 415 55

arcjet

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

9K 32 2