A

AgentGuards

LLM security guardrails for Codex with enforcing hooks and MCP tools: jailbreak and prompt-injection detection, web-content scanning, data-exfiltration blocking, and destructive-command authorization

alelaguard/agentguards-plugins · unreleased source · 02a5c05 · Tools & Integrations

alelaguardOwner verifiedcaution
InstallSource
60Follow0

Trust Score

60

Security

59

Surfaces

27

What is AgentGuards?

AgentGuards is a published tools & integrations plugin for AI coding agents in the codex ecosystem, developed by alelaguard and distributed through the HOL AI plugin registry. LLM security guardrails for Codex with enforcing hooks and MCP tools: jailbreak and prompt-injection detection, web-content scanning, data-exfiltration blocking, and destructive-command authorization

Canonical slug
alelaguard/agentguards-plugins
Version
unreleased source · 02a5c05 · updated Oct 9, 2026

Trust & Reputation

HOL Trust Score
60

Factor Analysis

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
64pts
Maintenance
55pts
MCP Posture
100pts
Plugin Security
59pts
Provenance
70pts
Publisher Quality
75pts

Registry Snapshot

Publisher verification
No
Marketplace source
Unknown
Scanner
Broker fallback
Safety label
caution
Digest verified
Yes
27 bundled skills — copy or download SKILL.mdOpen skills

Trust & reputation

Trust & Reputation

HOL Trust Score
60

Factor Analysis

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
64pts
Maintenance
55pts
MCP Posture
100pts
Plugin Security
59pts
Provenance
70pts
Publisher Quality
75pts

Provenance

Plugin root
.
Source repo
https://github.com/alelaguard/agentguards-plugins
Source commit
02a5c05749bf…
Publisher verified
No
Owner verified
@alelaguard

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

Verified badge not detected

Add the HOL verified badge to the repository README to score +2% trust. Plugin owners can open that pull request from Guard Plugins.

Security Posture

caution
Safety label
59
Security score
0
High findings
Provider
registry-broker-fallback
Grade
F · caution
Version
Unknown
cisco-skill-scanner: unknown

Findings

mediumpublishabilitypublishability.link.missing.websiteURL

websiteURL should be present for marketplace readiness.

mediumpublishabilitypublishability.link.missing.privacyPolicyURL

privacyPolicyURL should be present for marketplace readiness.

mediumpublishabilitypublishability.link.missing.termsOfServiceURL

termsOfServiceURL should be present for marketplace readiness.

lowoperational-securitysupply-chain.lockfile-missing

Repository snapshot does not include a lockfile.

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

AgentGuards — Frequently asked questions

What is AgentGuards?
AgentGuards is an AI plugin in the HOL registry. LLM security guardrails for Codex with enforcing hooks and MCP tools: jailbreak and prompt-injection detection, web-content scanning, data-exfiltration blocking, and destructive-command authorization
How do I install AgentGuards?
Install AgentGuards in your harness: Source — https://github.com/alelaguard/agentguards-plugins/releases; Any agent — npx skills add alelaguard/agentguards-plugins. Full step-by-step guidance is on the HOL plugin page.
How do I install AgentGuards in Source?
To install AgentGuards in Source, start with https://github.com/alelaguard/agentguards-plugins/releases. The complete step-by-step install guide for Source is on the HOL plugin page.
Is AgentGuards free?
Pricing for AgentGuards is published on its HOL plugin page when the maker schedules a launch.
Who publishes AgentGuards?
AgentGuards is published by alelaguard and listed on HOL.
Is AgentGuards available now?
AgentGuards availability is listed on its HOL plugin page.

Install Guidance

Install in Source

Install from a native release archive or the assessed source revision.

Install guide
  1. 1

    Download the release archive

    Use a published GitHub release archive. The catalog version is the package version at the assessed commit.

    shell
  2. 2

    Follow the publisher install guide

    https://github.com/alelaguard/agentguards-plugins/blob/02a5c05749bfefa5e355572c445b6f0195b2c10a/docs/INSTALL.md

Plugin Manifest

{
  "name": "agentguards-plugins",
  "version": "0.0.0",
  "description": "LLM security guardrails for Codex with enforcing hooks and MCP tools: jailbreak and prompt-injection detection, web-content scanning, data-exfiltration blocking, and destructive-command authorization",
  "repository": "https://github.com/alelaguard/agentguards-plugins",
  "homepage": "https://github.com/alelaguard/agentguards-plugins",
  "interface": {
    "displayName": "AgentGuards",
    "developerName": "alelaguard",
    "category": "Tools & Integrations"
  },
  "skills": "./",
  "holManifestOrigin": "synthesized",
  "registryIndexVersion": 5
}

Skills

27 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli

  • guardrails

    claude-selfhosted/skills/guardrails/SKILL.md

    AgentGuards security guardrails for a self-hosted appliance — explains that enforcement is fully automatic via hooks and there is nothing further to call. Load this if asked how guardrails are enforced in this variant, or why no agentguards MCP tools are available.

    Raw SKILL.md

  • setup

    claude-selfhosted/skills/setup/SKILL.md

    Set up and verify AgentGuards in Claude Code against a self-hosted appliance. Use when the user runs /agentguards:setup, asks to configure AgentGuards, set their URL/API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    claude-selfhosted/skills/status/SKILL.md

    Report AgentGuards guardrail status for a self-hosted appliance. Use when the user runs /agentguards:status or asks whether AgentGuards is active, healthy, or correctly configured.

    Raw SKILL.md

  • guardrails

    claude/skills/guardrails/SKILL.md

    How AgentGuards enforces its guardrails in Claude Code — fully automatic, via hooks, with nothing for you to call. Load this if asked how AgentGuards works, whether you need to screen something yourself, or why no agentguards check_input / authorize_action tools are available.

    Raw SKILL.md

  • setup

    claude/skills/setup/SKILL.md

    Set up and verify AgentGuards in Claude Code. Use when the user runs /agentguards:setup, asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    claude/skills/status/SKILL.md

    Report AgentGuards guardrail status. Use when the user runs /agentguards:status or asks whether AgentGuards is active, healthy, or correctly configured.

    Raw SKILL.md

  • guardrails

    codex-selfhosted/skills/guardrails/SKILL.md

    AgentGuards security guardrails for a self-hosted appliance — explains that enforcement is fully automatic via hooks and there is nothing further to call. Load this if asked how guardrails are enforced in this variant, or why no agentguards MCP tools are available.

    Raw SKILL.md

  • setup

    codex-selfhosted/skills/setup/SKILL.md

    Set up and verify AgentGuards in Codex against a self-hosted appliance. Use when the user asks to configure AgentGuards, set their URL/API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    codex-selfhosted/skills/status/SKILL.md

    Report AgentGuards guardrail status for a self-hosted appliance. Use when the user asks whether AgentGuards is active, healthy, or correctly configured in Codex.

    Raw SKILL.md

  • guardrails

    codex/skills/guardrails/SKILL.md

    How AgentGuards enforces its guardrails in Codex — fully automatic, via hooks, with nothing for you to call. Load this if asked how AgentGuards works, whether you need to screen something yourself, or why no agentguards check_input / authorize_action tools are available.

    Raw SKILL.md

  • setup

    codex/skills/setup/SKILL.md

    Set up and verify AgentGuards in Codex. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    codex/skills/status/SKILL.md

    Report AgentGuards guardrail status. Use when the user asks whether AgentGuards is active, healthy, or correctly configured in Codex.

    Raw SKILL.md

  • guardrails

    copilot-selfhosted/skills/guardrails/SKILL.md

    AgentGuards security guardrails for a self-hosted appliance — explains that enforcement is fully automatic via hooks and there is nothing further to call. Load this if asked how guardrails are enforced in this variant, or why no agentguards MCP tools are available.

    Raw SKILL.md

  • setup

    copilot-selfhosted/skills/setup/SKILL.md

    Set up and verify AgentGuards in GitHub Copilot CLI against a self-hosted appliance. Use when the user asks to configure AgentGuards, set their URL/API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    copilot-selfhosted/skills/status/SKILL.md

    Report AgentGuards guardrail status for a self-hosted appliance. Use when the user asks whether AgentGuards is active, healthy, or correctly configured in Copilot CLI.

    Raw SKILL.md

  • guardrails

    copilot/skills/guardrails/SKILL.md

    AgentGuards security guardrails — the mandatory input-screening, web-content, and destructive-command checking workflow. Load and apply this at the START of EVERY request, before using any content fetched from the web (curl/wget/HTTP libraries), and before suggesting any destructive command. Covers check_input, authorize_action, and the required block-message format.

    Raw SKILL.md

  • setup

    copilot/skills/setup/SKILL.md

    Set up and verify AgentGuards in GitHub Copilot CLI. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    copilot/skills/status/SKILL.md

    Report AgentGuards guardrail status. Use when the user asks whether AgentGuards is active, healthy, or correctly configured in GitHub Copilot CLI.

    Raw SKILL.md

  • guardrails

    gemini-selfhosted/skills/guardrails/SKILL.md

    AgentGuards security guardrails for a self-hosted appliance — explains that enforcement is fully automatic via hooks and there is nothing further to call. Load this if asked how guardrails are enforced in this variant, or why no agentguards MCP tools are available.

    Raw SKILL.md

  • setup

    gemini-selfhosted/skills/setup/SKILL.md

    Set up and verify AgentGuards in Gemini CLI against a self-hosted appliance. Use when the user asks to configure AgentGuards, set their URL/API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    gemini-selfhosted/skills/status/SKILL.md

    Report AgentGuards guardrail status for a self-hosted appliance. Use when the user asks whether AgentGuards is active, healthy, or correctly configured in Gemini CLI.

    Raw SKILL.md

  • guardrails

    gemini/skills/guardrails/SKILL.md

    AgentGuards security guardrails — the mandatory input-screening, web-content, and destructive-command checking workflow. Load and apply this at the START of EVERY request, before using any content fetched from the web (curl/wget/web_fetch/google_web_search), and before suggesting any destructive command. Covers check_input, authorize_action, and the required block-message format.

    Raw SKILL.md

  • setup

    gemini/skills/setup/SKILL.md

    Set up and verify AgentGuards in Gemini CLI. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    gemini/skills/status/SKILL.md

    Report AgentGuards guardrail status. Use when the user asks whether AgentGuards is active, healthy, or correctly configured in Gemini CLI.

    Raw SKILL.md

  • guardrails

    opencode/skills/guardrails/SKILL.md

    AgentGuards security guardrails — the mandatory input-screening, web-content, and destructive-command checking workflow. Load and apply this at the START of EVERY request, before using any content fetched from the web (webfetch/curl/wget), and before suggesting any destructive command. Covers check_input, authorize_action, and the required block-message format.

    Raw SKILL.md

  • setup

    opencode/skills/setup/SKILL.md

    Set up and verify AgentGuards in OpenCode. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.

    Raw SKILL.md

  • status

    opencode/skills/status/SKILL.md

    Report AgentGuards guardrail status. Use when the user asks whether AgentGuards is active, healthy, or correctly configured.

    Raw SKILL.md

File Inventory

.codex-plugin/plugin.json

plugin-manifest

570 bytes

e455a948acbe2093…

claude-selfhosted/skills/guardrails/SKILL.md

skill

2,003 bytes

d2ef61a5a374b549…

claude-selfhosted/skills/setup/SKILL.md

skill

2,343 bytes

e1cd38de1b36e63c…

claude-selfhosted/skills/status/SKILL.md

skill

1,571 bytes

c7ed886c42730bf2…

claude/skills/guardrails/SKILL.md

skill

1,638 bytes

4661ef47f591f1ae…

claude/skills/setup/SKILL.md

skill

9,709 bytes

6f77e2d5b8ea947b…

claude/skills/status/SKILL.md

skill

2,243 bytes

76fab1503a17370e…

codex-selfhosted/skills/guardrails/SKILL.md

skill

1,890 bytes

94e1edac1b25a43c…

codex-selfhosted/skills/setup/SKILL.md

skill

2,607 bytes

c3164d4481c79712…

codex-selfhosted/skills/status/SKILL.md

skill

1,578 bytes

f41b82b271557008…

codex/skills/guardrails/SKILL.md

skill

2,206 bytes

dcc5859f05e8c8b5…

codex/skills/setup/SKILL.md

skill

2,044 bytes

2b59667c9ed1c0be…

codex/skills/status/SKILL.md

skill

2,411 bytes

bfb2e6d0af93f283…

copilot-selfhosted/skills/guardrails/SKILL.md

skill

1,976 bytes

3b7395a9392509a5…

copilot-selfhosted/skills/setup/SKILL.md

skill

2,209 bytes

5a644219bbba90cc…

copilot-selfhosted/skills/status/SKILL.md

skill

1,500 bytes

34bfce3fd64bdccd…

copilot/skills/guardrails/SKILL.md

skill

4,625 bytes

3f8163fcbcf7448a…

copilot/skills/setup/SKILL.md

skill

2,026 bytes

1403000e3008e74a…

copilot/skills/status/SKILL.md

skill

1,101 bytes

8a25991456f52bf3…

gemini-selfhosted/skills/guardrails/SKILL.md

skill

1,849 bytes

59c8c2d9006bd119…

gemini-selfhosted/skills/setup/SKILL.md

skill

2,205 bytes

5225caf95c2b60bd…

gemini-selfhosted/skills/status/SKILL.md

skill

1,499 bytes

1e860610f3f99ab4…

gemini/skills/guardrails/SKILL.md

skill

4,705 bytes

a0dedc210a6818aa…

gemini/skills/setup/SKILL.md

skill

2,012 bytes

662c67c353927c27…

gemini/skills/status/SKILL.md

skill

1,077 bytes

73eff1d78a3e827a…

opencode/skills/guardrails/SKILL.md

skill

4,753 bytes

b9508283d50aa405…

opencode/skills/setup/SKILL.md

skill

2,368 bytes

d87d693ab8d8114b…

opencode/skills/status/SKILL.md

skill

968 bytes

33f8492f9bdfb2e7…

README.md

file

5,299 bytes

57c8b96f47681ea3…

README.md

file

5,299 bytes

57c8b96f47681ea3…

SECURITY.md

file

1,196 bytes

da436fd15066f592…