AgentGuards checks the things an AI agent is about to trust or run. - Scan untrusted text (web pages, emails, documents, issues, other tools' output) for prompt injection, jailbreak attempts, leaked secrets and personal data before acting on it. - Check a shell command before running it: destructive deletes, credential reads, data exfiltration, force pushes and infrastructure changes are flagged with a risk level and a reason. - Scan source code for security issues and hardcoded secrets before committing or running it. Who it's for: developers using ChatGPT or Codex with untrusted inputs or shell access. Requires an AgentGuards account (you sign in when you connect). Scan results also appear in your AgentGuards dashboard. Limitations: the tools scan only what they are given, when they are called. They do not intercept anything automatically, and they never run, change or delete anything themselves.