
Scanner that checks agent skills for prompt injection, exfiltration and other risks
- Open source
- Open-source agent
- 26.7K GitHub stars
- Security

Scanner that checks agent skills for prompt injection, exfiltration and other risks
Zero-log MCP server with 49 tools for AI guardrails, secret scanning and EU compliance
Checks a shop, payment link, paid API or token before an agent pays, plus injection scans
Runs locallyScan PDF, Office, RTF and HTML files for hidden text before an agent reads them
Scan prompts for injection and PII, and audit LLM SDK usage from an MCP client
Scan PDFs and Office files for malware and hidden prompt injection before an AI reads them
Local input firewall that scans text, files and MCP metadata for prompt injection
Runs locallyLint a SKILL.md for missing triggers, leaked secrets and injection markers before install
Not checked yetChecked inbound email, held outbound sends and approved Meet calls for AI agents
Not checked yetFlags fake engagement and prompt injection in AI-agent job board listings
Runs locallyAudit AI agent skills for safety with static, semantic, adversarial and supply-chain scans
Runs locallySafety grades for MCP servers and APIs, with wrap and lockfile modes to catch tool changes
Runs locallyChecks one inbound email and returns structured findings on scams, paid links and pitches
Runs locallyPrompt-injection scanner and tool-call gate for AI agents, run locally over stdio
Runs locallyScan text, tool output and web pages for prompt injection, secrets, PII and SSRF URLs
Not checked yetStatic security scanner for MCP servers, agent skills and npm or PyPI packages
Runs locally
Let an agent pay on NEAR through a vault whose rules a smart contract enforces
Runs locallyLocal security layer for coding agents: secret redaction, injection checks and MCP proxy
Runs locally
Self-hosted fleet of persistent, logged-in stealth Chrome sessions for AI agents
Runs locallyLet your coding agent publish a card, find matching agents and negotiate behind a firewall
Not checked yet
Scan prompts, tool definitions and model output for injection, and guard tool calls
Runs locallyReview and block risky AI agent actions, installs and MCP calls on your machine
Runs locallySigned, sealed handoffs between AI agents, with trust decided by the receiver
Runs locallyScan MCP configs for leaked secrets and poisoned tools, and review AI-written code
Not checked yetEmail MCP server for Gmail, Outlook and IMAP that fences messages against prompt injection
Runs locallyLocal file inspector and guarded editor that flags hidden content and text aimed at AI
Runs locallyPay-per-call prompt-injection scanner that cleans pages before an agent reads them
Not checked yetScans GitHub repos and shell commands for malware tricks before an agent runs them
Not checked yetSecrets manager MCP server that runs commands with API keys the model never sees
Runs locallyScreen untrusted text for prompt injection and jailbreaks before it reaches your LLM
Not checked yet