1,796,946 packages matching “data-poisoning”
hlido-mcp-guard
v0.1.0 · 28 days ago
Check an MCP server's independent Hlido trust verdict before it starts — a zero-dependency, no-API-key runtime guardrail for Claude Code, Cursor, Cline, and any stdio MCP client.
No known vulnerabilities
@rizom/ops
v0.2.0-alpha.263 · 1 minute ago
Operator CLI for managing private brain fleet registry repos
No known vulnerabilities
@commercial/bourne
v2.0.0 · 6 years ago
JSON parse with prototype poisoning protection
No known vulnerabilities
mcp-agentgate
v0.55.0 · 2 hours ago
Scan, lock, and gate your MCP servers — npm audit + lockfile + CI drift gate for the MCP era
No known vulnerabilities
mcp-shield
v1.0.4 · 1 year ago
Security scanner for MCP servers
No known vulnerabilities
@mcp-contracts/cli
v0.7.2 · 18 hours ago
CLI tool for capturing and diffing MCP tool schemas
No known vulnerabilities
@absolutejs/agent-conformance
v0.15.1 · 7 days ago
Provider-neutral adversarial conformance for agent security plus A2A, MCP, Arazzo, and WebMCP standards.
No known vulnerabilities
@graphorin/memory
v0.15.1 · 16 days ago
Six-tier memory system for the Graphorin framework: createMemory() facade with working / session / episodic / semantic / procedural / shared sub-modules, eleven memory tools wired into @graphorin/tools, hybrid vector + FTS5 search composed through Recipro
No known vulnerabilities
memotrust
v0.1.5 · 1 month ago
Verified memory for AI agents — agents propose, evidence verifies, recall returns only earned trust.
No known vulnerabilities
n8n-nodes-soterai
v0.3.3 · 8 days ago
SoterAI helps protect n8n AI workflows by detecting prompt injection, jailbreaks, secrets, PII, and unsafe AI instructions.
No known vulnerabilities
kelet
v0.11.0 · 1 month ago
Kelet TypeScript SDK for AI observability
No known vulnerabilities
hexora
v2.0.0 · 2 months ago
**Web3 Security SDK** — detect address poisoning attacks, phishing domains, and malicious transactions before users lose funds.
No known vulnerabilities
@axiorank/mcpaudit
v0.3.1 · 25 days ago
Scan any MCP server for prompt injection, tool poisoning, leaked secrets, and destructive capabilities. One command, no key, no signup.
No known vulnerabilities
@elliotllliu/agent-shield
v0.16.0 · 4 months ago
Multi-engine AI agent security scanner — one scan, four engines, one report
No known vulnerabilities
movehat
v0.9.0 · 1 day ago
Hardhat-like development framework for Movement L1 smart contracts
No known vulnerabilities
harden-urls
v1.0.0 · 9 months ago
🛡️ URL hardening and sanitization utilities with safe defaults, pattern-based allow/block lists, and cleanup for links and mailto URIs.
No known vulnerabilities
agentshield-sdk
v14.2.2 · 2 months ago
SOTA AI agent security SDK. F1 1.000 on BIPIA/HackAPrompt/MCPTox/Multilingual benchmarks. 400+ exports, 100+ modules. Zero dependencies, runs locally.
No known vulnerabilities
reliable-caching
v0.1.7 · 1 month ago
This package is the code support for book "Node Reliable Caching"
No known vulnerabilities
pi-multi-account
v1.14.3 · 6 days ago
Automatic multi-account failover & rotation for Pi Agent across Anthropic (Claude), OpenAI/ChatGPT Codex, Qwen/Alibaba, and Ollama. Auto-discovers authenticated accounts, grows the rotation on login, and drops accounts on logout, expiry, or quota/rate-lim
No known vulnerabilities
dcl-social-client
v1.28.0 · 2 years ago
A client to handle messaging and friendship between Decentraland users
No known vulnerabilities