Search

Enforra policy enforcement integration for Model Context Protocol (MCP) tool handlers.

Scan untrusted content for prompt injection and check link reputation before an agent acts

MCP server for JADX-AI Plugin

Policy-enforcing proxy in front of any Splunk MCP server

Dynamic exploitability testing for AI agents and the MCP servers they use

Semantic prompt-injection & tool-poisoning linter for MCP servers. Precision-first, 100% local — tells real injection apart from legitimate tool descriptions.

Arm any MCP-capable agent to autonomously red-team a target LLM. Microsoft PyRIT exposed as 31 composable MCP tools: attacks, scoring, converters & scenarios

Semantic request filtering and scope control for AI apps.

Pi package for npm/supply-chain security workflows: Socket MCP bridge extension, npm security best-practices skill, and related tooling.

Chained Harm & Injection Measurement for Evaluating Risks in Agents — a red-team research framework that tests hosted models, agentic apps, RAG pipelines, MCP servers, AI coding assistants, macOS desktop apps, and browser extensions against context-pollution, prompt-injection, and chain-composition attacks.

Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.

轻量级架构记录工具 - Command-line tools for working with Architecture Decision Records

Runtime gateway detecting prompt-injection and jailbreak for LLM agents. 2.4 ms, F1 0.921.

Runs the DeFade MCP stdio server. Thin alias for the `defade` package, which carries the implementation — `npx defade-mcp` and `npx -p defade defade-mcp` are equivalent.

Runtime red-team harness for live MCP servers. Attacks as real roles to find authz/RBAC bypasses a static manifest scan can't see. The offense leg of an agent-governance suite (Warden governs, Crumb attributes, Siege proves it holds).

TypeScript SDK for verifying and auditing MCP tool passports — OpenTrust trust registry client

MCP server for the Frida reverse engineering toolkit.

Open standard MCP server for Zero-Trust Data Sanitization (ZTDS RFC v1.0). In-memory PII masking.

Local action firewall for AI agents: scans what the agent reads, taints the session, blocks dangerous follow-up actions

Find payment logic flaws in Razorpay and Stripe checkouts - client-trusted amounts, rupee/paise bugs, unverified webhooks