Tool Poisoning Python Packages

sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

agent-audit-kit

Static scanner for MCP-connected AI agent pipelines — 225 rules across 11 categories, 12 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.

intentprobe

Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.

deconvolute

Policy-as-code enforcement and observability for MCP tool calls. Wraps AI agent sessions with cryptographic integrity checks, argument-level CEL policies, and a full audit trail.

bawbel-mcp

MCP server exposing Bawbel Scanner as agent-callable tools. Scan MCP servers, skill files, and system prompts for AVE vulnerabilities mid-conversation.

mcp-fence

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, sandbox runner, and report generator for Model Context Protocol servers.

mseep-mcp-fence

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.

clawguard-core

Security scanner for AI agents — 42+ regex patterns detecting prompt injections, jailbreaks, data exfiltration, and social engineering. Zero dependencies, <10ms.

guardmcp

Security scanner for MCP server configurations. Detects secrets, injection, auth issues, and maps to OWASP MCP Top 10.