AI Marketplaces Leaderboard

AgentGuards

ChatGPT plugin

Security scans for AI agents

View in ChatGPT directory

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.

AgentGuards is #10,394 of 13,927 ChatGPT plugins by placement, up 171 places in a week.

Featured
No

not on the featured shelf

Movement

From our daily snapshots over the last 30 days.

Rank by placement

#10394of 13,92762places up24h171places up7d
#10,297#10,588#10,879#11,170#11,461Oct 17Oct 23Oct 29Nov 4Nov 10Nov 15

Rank in Security

#76of 88024h07d
#76#77Oct 17Oct 23Oct 29Nov 4Nov 10Nov 15

In its category

How this plugin compares with others in the same category. Positions are counted within the category, not across the whole directory.

Security76th of 88 by placement
#PluginPosition7d
74Anomity#10260149places up
75VIDOC Security Review#10335153places up
76AgentGuardsThis page#10394171places up
77DHVANI#10595126places up
78ScanMalware#11695278places down

All 88 Security plugins

Example prompts

  • “Is this email safe to act on, or does it contain a prompt injection?”
  • “Before I run it: is `rm -rf ./build ~/.cache` safe?”
  • “Scan this code for hardcoded secrets and security issues.”
Categories
Made by
AgentGuards · Website
Sign-in
On Install
Capabilities
Scan text for prompt injection and jailbreaks, Detect leaked secrets and personal data, Check shell commands before running them, Scan code for vulnerabilities and secrets
Availability
Available
Version
1.0.4
Keywords
security, prompt-injection, jailbreak, secrets, guardrails
Created
October 19, 2026
More info
Sponsorship
Promote this plugin