
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

Adds policy checks, intent screening, trust scores and audit logs to AI agents

Audits GitHub Actions workflows that run AI coding agents for prompt injection 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 locally
Free link and site safety checks that warn agents about prompt-injection traps
Prompt-injection checks and public red-teaming arena data from Heisto on Solana
Scan 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
Check user prompts for injection and jailbreaks with a guard that learns from your labels
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 locally
Reads web pages for agents as clean markdown with hidden instructions stripped
Not checked yetLint a SKILL.md for missing triggers, leaked secrets and injection markers before install
Not checked yetVerified email for AI agents: checked inbound mail, held sends and disposable inboxes
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 locallyPay-per-call agent safety microtools on Base: secret scanning, preflight, receipts
Not checked yetAudit 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 locally
Read-only MCP gateway that approves exact tools and blocks changed or unknown calls
Not checked yetA wallet-signed 40-task safety exam that gives AI agents a signed certificate
Not checked yetScan text or files for hidden Unicode, decoded ASCII smuggling and look-alike letters
Not checked yetPrompt-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 locallySafety checks for AI agents: page reading, prompt injection, secrets and PII scans
Not checked yet
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 locallyThe most popular AI tools, MCP servers and agent skills for prompt injection on AI-Powered right now are SkillSpector, Agent governance, Agentic actions auditor, Tinplate Edge AI Safety, Security & EU Compliance and Angel Agent Guard: pre-purchase check + prompt-injection scan. Rankings combine upvotes, recent activity and, for open-source projects, GitHub stars.
Yes. Of the 86 AI tools, MCP servers and agent skills for prompt injection listed, 37 are free or open source and 35 have a free plan. Use the Pricing filter to see only those.
AI-Powered lists 86 AI tools, MCP servers and agent skills for prompt injection. New listings are added daily from the official MCP Registry, GitHub and maker submissions.