Keyword: prompt-injection
- agent-input-sanitizerReleased9h agoVersion1.3.4
Defend an agent against hidden-content injection: strip payload-capable invisible Unicode and ANSI, splice out human-invisible HTML, and flag data-exfil URLs in untrusted text before any model sees it.
- fullcourtdefense-cliReleased5d agoVersion1.6.13
Full Court Defense CLI — security scanning for AI agents from your terminal
- shellwardReleased5d agoVersion0.7.21
AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.
- @drakon-systems/shieldcortex-realtimeReleased1h agoVersion4.44.0
OpenClaw plugin for ShieldCortex real-time defence scanning and optional memory extraction.
- salus-appsecReleased9m agoVersion1.0.12
Salus — CLI de AppSec com IA. Code review, análise de vulnerabilidades, hardening defensivo e auditoria AI/LLM. Modo BYOK (Bring Your Own Key).
- @solongate/proxyReleased23h agoVersion0.49.0
AI tool security proxy — protect any AI tool server with customizable policies, path/command constraints, rate limiting, and audit logging. Zero code changes required.
- @roleplay-sh/cliReleased6d agoVersion0.1.12
Included local runner for roleplay.sh social-engineering tests.
- @opena2a/aicomplyReleased3d agoVersion2.2.2
Inline PII, credential, and regulated-data classifier for AI agent I/O. Dual-layer: deterministic regex + optional semantic Guard. Library + CLI.
- ai-sdk-guardrailsReleased21h agoVersion6.0.0
Input and output guardrails middleware for Vercel AI SDK.
- zyrax-guardReleasedyesterdayVersion0.9.0
Audit AI agent configs (prompt injection, rogue MCP servers) and vet packages — local, zero-dependency. CLI + MCP server.
- astro-webmcpReleased6d agoVersion0.3.0
Astro integration that exposes your site content via WebMCP for AI agents
- ferret-scanReleased2d agoVersion2.9.0
Static security scanner for AI CLI and MCP configurations — detects credential leaks, prompt injection, jailbreaks, and supply chain risks
- substrai-guardrailgraphReleased7h agoVersion1.3.0
Composable AI safety pipeline framework with industry compliance packs (HIPAA, SOX, GDPR, FedRAMP)
- mintmarkReleased23h agoVersion0.2.0
The trust layer for the MCP supply chain - fingerprint MCP servers and detect rug-pulls/drift from your terminal.
- ghostfilter-aiReleasedyesterdayVersion0.1.2
Safety firewall SDK for humans and AI agents — scan untrusted text for scams/phishing and prompt-injection before you (or your agent) trust it.
- @cerberus-ai/coreReleasedyesterdayVersion3.0.1
Runtime security for AI agent tool execution. Detects, correlates, and interrupts guarded Lethal Trifecta attack paths.
- @permanentlymobile/pm-aidReleased5d agoVersion1.1.0
PM AID Full -- AI agent defense scanner. 74 shipped JS-native modules, including refusal-bait scanner evasion, offline ED25519 licensing, Basic/Full module tiers, and zero-retention local scans.
- decoy-redteamReleased6d agoVersion0.6.0
Autonomous red team tool for MCP servers. Finds exploitable vulnerabilities before attackers do.
- vigile-scanReleased19h agoVersion3.0.1
Security scanner for AI agent tools — detect tool poisoning, permission abuse, and supply chain attacks in MCP servers and agent skills
- decoy-scanReleased6d agoVersion0.10.0
Security scanner for MCP server configurations. Finds risky tools, vulnerable packages, and suspicious servers across Claude Desktop, Cursor, VS Code, and more.
- @grovetech/defenderReleased2d agoVersion0.3.0
Active runtime protection for vibe-coded apps — drops in as Express middleware (web + AI layer), blocks prompt injection, PII leaks, and sensitive paths in real time. By Grovetech AI.
- jaku.shReleasedyesterdayVersion1.2.1
JAKU (呪) — Autonomous Security & Quality Intelligence Agent for vibe-coded apps. XSS, SQLi, prompt injection, QA testing, and attack chain correlation in one command.
- agent-defenderReleased48m agoVersion1.0.1
Drop-in security guardrails for AI agents. Blocks unauthorized tool calls, exfiltration, prompt injection, and secret leaks — in-process, sub-millisecond, zero network.
- @kaditang/agent-payment-guardReleased58m agoVersion0.2.0
Pre-pay risk gate for autonomous payment agents — block prompt-injected destinations, intent mismatches, overcharges and drains before your agent signs. Backed by 402Sentinel; drops into the Claude Agent SDK, x402/AgentKit, or any framework.
- @sentinelrn/coreReleased1h agoVersion0.1.1
Application Trust Runtime for React Native — runtime integrity and AI security engine.