Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
SafePrompt
MCP serversDetect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
@safeprompt.dev/mcp@0.1.1 -
PromptGuard Scan MCP
MCP serversPaid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
-
ascript-mcp
MCP serversControl Android/iOS/Windows devices from Claude, Cursor, and other AI tools. iOS without jailbreak.
ascript-mcp@1.7.0 -
Koma Gate MCP
MCP serversClassifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.
koma-gate-mcp@0.1.1 -
icme-preflight
MCP serversJailbreak-proof AI guardrails. Automated Reasoning SMT solver, not an LLM. ZK proofs included.
-
Icemoon — control a real iPhone with AI
MCP serversControl real, physical iPhones with AI: screen reading, human-like touch, no jailbreak.
icemoon-mcp@1.0.1 -
Prompt Compass
MCP serversDecision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.
@mpcfintech/prompt-compass-mcp@1.0.1 -
LLM Security Scanner
MCP serversLLM agent security scan: injection, jailbreak, tool abuse probes plus guardrail audit.
-
AI Agent Security Scanner
MCP serversSecurity scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
-
Habits prompt-injection guard
MCP serversCheck user prompts for injection/jailbreaks; your own guard learns from your labels. Works keyless.
-
LLM Red-Team Scanner
MCP serversLLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails
-
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.git -
ai-security-corpus
Skills5,660 AI security links: prompt injection, LLM & AI agent security, MCP, coding agents, agent skills & supply chain, red teaming, guardrails, sandboxing, incidents & CVEs, governance. 570 arXiv papers, 1,155 GitHub repos, 570 X posts, 29 categories of plain markdown you can grep, diff and fork. Obsidian vault export. Added, not endorsed.
git clone https://github.com/AnthonyHerman/ai-security-corpus.git -
Add AI protection
Prompts--- name: add-ai-protection license: Apache-2.0 description: Protect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts, block PII and sensitive info from leaking in responses…
-
Act as Chimera, an AI-powered prompt optimization and jailbreak research system. You are equipped with a FastAPI backend and Next.js frontend, providing advanced prompt transformation techniques, multi-provider LLM…
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.