Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
InjectScan
MCP serversPrompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools
-
AgentRead
MCP serversTurn URLs, PDFs and DOCX into clean Markdown for agents, plus prompt-injection scanning
-
capabilitymap-nexus-mcp
MCP serversGitHub Capability Router (666 repos, 96.4% token savings) & 5-Vector Prompt-Injection Firewall.
-
Agent Readiness Auditor
MCP serversAudits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
agent-readiness-auditor@0.5.0 -
Nullcone Threat Intelligence
MCP serversReal-time threat intel for AI agents: 890K+ IOCs incl. prompt-injection & AI-skill threats
-
Agent-Shield
MCP serversSecurity scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
-
Aletheia Runtime Safety & Scope Creep Filter
MCP serversDeterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls
aletheia-mcp@0.3.1 -
APIShield WAF v4.0 MCP
MCP servers50-vector prompt-injection, llms.txt poisoning, SSRF & OpenAPI scanner ($1 USDC).
-
Bastion Helix Agent Lens
MCP serversWeb pages for AI agents: may-I-use checks, prompt-injection flags, Markdown, JSON, screenshots
-
Power Strip Security
MCP serversPrompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402.
power-strip-security-mcp@0.2.0 -
Mails.ai — Agent Email
MCP serversA real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.
@mailsai/mcp-server@0.5.0 -
site-audit
MCP serversDiscover a site's pages from its sitemap and sample them for WCAG and prompt-injection risk.
-
prompt-guard-mcp
MCP serversScans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
-
Agent Skill & Config Security Audit
MCP serversScan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.
-
IA-QA Security — 30 tools
MCP serversAgent security: prompt injection, PII & secret scans, TLS/header/CORS audits, MCP checks. Free.
-
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
tripwire-guard@0.4.2 -
Safe Web Reader for AI
MCP serversWeb pages, JavaScript sites and PDFs to clean Markdown for AI agents, prompt injection removed.
-
SCRIPTMASTERLABS — SML agent-safety
MCP serversThree fast safety checks for agents, each with a signed hash-chained receipt: (1) prompt-injection c
-
skills-janitor
SkillsTinder for your Claude Code skills, subagents and MCP servers. Swipe away what wastes context, scan for prompt injection, get honest token costs. Fixes what it finds and actually deletes. Zero dependencies, Claude Code + Codex.
git clone https://github.com/khendzel/skills-janitor.git -
Scan PDFs, Office docs, and RAG files for malware exploits, macros, CVEs, and AI prompt injection.
malwaretracker-mcp@2.3.0 -
aizee
SkillsThe policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memory, tamper-evident audit. pip install aizee
git clone https://github.com/m3taz-ahmed/aizee.git -
hermes-jailbench
SkillsZero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench
git clone https://github.com/hermes-labs-ai/hermes-jailbench.git -
Singularity - MCP Discovery & Security Gateway
MCP serversFind, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
-
agent-guard
SkillsScan AI agent skills, plugins, MCP servers, and CLI tools (npm/PyPI/Go, cargo, release binaries, curl|bash installers) for malicious code before installation - one scan, every agent (Claude Code, Codex, Gemini, Hermes, OpenClaw). Powered by NVIDIA SkillSpector, Cisco mcp-scanner, Datadog GuardDog, VirusTotal + malcontent.
git clone https://github.com/elliottwaves-20/agent-guard.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.