P

Penthera

Elite offline cyber security agent for all your code, sites and apps, rule-based

danoszz/penthera · v2.4.0 · Development & Workflow

by danoszzOwner verifiedAwesome AI Plugins

The problem
You ship faster than anyone can check your work. A coding agent writes the feature, you deploy, and nobody looked at the secrets in the repo, the new dependency, the headers, or the AI tool config that can run commands on your machine.

Follow0
Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is Penthera a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Claude Code
  • MCP
  • Antigravity CLI
  • 2 skills
  • 1 MCP server

Before you install

Sign-in
Not declared
Declared access
Not declared
License
MIT

Check before relying on it

  • Some security checks did not finish: Cisco skill scan and Cisco MCP scan. See the evidence

About Penthera

How it works
Penthera is an open-source security agent that runs on your machine. One command (npx penthera --repo .) or one sentence to your coding agent checks your code (secrets, risky routes, missing checks), your dependencies (vulnerabilities, install scripts, malicious packages), your AI tools (MCP servers, hooks, skills) and your live site (passive). Rules decide every finding, not a model, so you can check each one. Offline: your code never leaves your machine. Hand the short brief to Claude Code or Cursor and let your agent fix it, with your consent.

Free, MIT. CLI, MCP server, Agent Skill, GitHub Action, Vercel check.

Who it's for
Solo devs and vibe coders shipping Next.js, Supabase, Stripe and Vercel apps with Claude Code, Cursor, v0 or Lovable, who have never run a security tool. Plain words, one thing to do first, no account.

What is Penthera?

Penthera is a published development & workflow plugin for AI coding agents that works with Claude Code, MCP and Antigravity CLI, developed by danoszz and distributed through the HOL AI plugin registry. MCP server: offline, read-only security checks for repositories, dependencies, MCP configuration and agent skills.

Canonical slug
danoszz/penthera
Version
v2.4.0 · updated Nov 18, 2026

Registry snapshot

Support the project
GitHub Sponsorsgithub.com
Owner verification
Verified on HOL as @danoszz
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Partial scan
Digest verified
Yes
2 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

On-Chain Verified
85

HOL Trust Score

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

Installability
100/100
Maintenance
100/100
MCP server setup
100/100
Plugin Security
95/100
Provenance
80/100
Publisher Quality
100/100

Provenance

Plugin root
.
Source repo
https://github.com/danoszz/penthera
Source commit
5fb4a5850c8f…
Publisher verified
Yes
Owner verified
@danoszz
Agent Plugins 1.0
Not detected

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.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Partial scan
Security result
95
Score from finished checks
0
High findings

Some checks did not finish: Cisco skill scan and Cisco MCP scan. No blocking issue was found in the checks that did finish, but this is not a passed scan.

Provider
codex-plugin-scanner
Grade
A · Excellent
Version
3.24.2
codex:hol-plugin-scanner-Iss7pJ / cisco-skill-scanner: failedcodex:hol-plugin-scanner-Iss7pJ / cisco-mcp-scanner: unavailable

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

20/20

6 checks

[claude:.] Operational Security

6/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

25/31

9 checks

[codex:.] Security

20/20

9 checks

[codex:.] Operational Security

6/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

N/A

3 checks · not applicable

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

[gemini:.] Gemini Extension

10/10

3 checks

[gemini:.] Security

20/20

6 checks

[gemini:.] Operational Security

6/6

5 checks

[gemini:.] Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

infomanifest-validationPLUGIN_JSON_INTERFACE_SHORTDESCRIPTION

The interface object is missing a valid "shortDescription" value.

Add a valid "shortDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_LONGDESCRIPTION

The interface object is missing a valid "longDescription" value.

Add a valid "longDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CATEGORY

The interface object is missing a valid "category" value.

Add a valid "category" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CAPABILITIES

The interface object is missing a valid "capabilities" value.

Add a valid "capabilities" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_WEBSITEURL

The interface field "websiteURL" must use HTTPS or point to a safe in-repo asset.

Update "websiteURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_PRIVACYPOLICYURL

The interface field "privacyPolicyURL" must use HTTPS or point to a safe in-repo asset.

Update "privacyPolicyURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_TERMSOFSERVICEURL

The interface field "termsOfServiceURL" must use HTTPS or point to a safe in-repo asset.

Update "termsOfServiceURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_COMPOSERICON

The interface field "composerIcon" must use HTTPS or point to a safe in-repo asset.

Update "composerIcon" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_LOGO

The interface field "logo" must use HTTPS or point to a safe in-repo asset.

Update "logo" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

  1. 1

    Add the marketplace

    Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.

    claude code
  2. 2

    Install the plugin

    Installs the penthera entry from the penthera marketplace.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell
  4. 4

    Check it is installed

    Lists installed plugins. The entry should appear as enabled.

    shell

To remove it later, run claude plugin uninstall penthera@penthera.

Did setup work in Claude Code?

No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W46, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Penthera x 4
1 / 4

Penthera x 4

Full size
Loading reviews

Plugin manifest

{
  "name": "penthera",
  "version": "2.4.0",
  "description": "Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every release.",
  "author": {
    "name": "Daan van der Zwaag",
    "url": "https://github.com/danoszz"
  },
  "homepage": "https://github.com/danoszz/penthera",
  "license": "MIT",
  "keywords": [
    "security",
    "scanner",
    "pentest",
    "owasp",
    "sarif",
    "secrets",
    "cli",
    "vibecoding",
    "supply-chain",
    "mcp",
    "ai-security",
    "nis2"
  ],
  "repository": "https://github.com/danoszz/penthera",
  "interface": {
    "displayName": "penthera",
    "developerName": "danoszz"
  },
  "skills": "./",
  "mcpServers": "./.registry/mcp.json",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/danoszz/penthera
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

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

Share
skills-cli
  • penthera

    plugin/skills/penthera/SKILL.md

    >

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • penthera

    skills/penthera/SKILL.md

    >

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File inventory

.claude-plugin/marketplace.json

file

605 bytes

e6436270bb4e9d4d…

.claude-plugin/plugin.json

file

549 bytes

cb7ab7f7834f4245…

.codex-plugin/plugin.json

plugin-manifest

665 bytes

f59933b23b72b9d3…

.github/dependabot.yml

file

998 bytes

a9d5338546e46da5…

.mcp.json

file

120 bytes

eebbd25bee7ecfbe…

.registry/mcp.json

mcp-config

82 bytes

88a24e7e13dcbf9b…

AGENTS.md

file

3,432 bytes

e44f92c8a92c41fc…

eslint.config.js

file

2,120 bytes

3708290c11c1e026…

gemini-extension.json

file

305 bytes

d523937515e78b7c…

LICENSE

file

1,416 bytes

f537cb591034fa57…

package-lock.json

file

91,803 bytes

ba38dd7bc73dbb03…

package.json

file

3,527 bytes

5da9e5537f6ba747…

plugin/skills/penthera/references/authorization.md

file

2,511 bytes

91fa4d7ae933a130…

plugin/skills/penthera/references/output-and-ci.md

file

3,242 bytes

c4f058a13c5b95d7…

plugin/skills/penthera/references/profiles-and-flags.md

file

3,649 bytes

f1f8eee654d70c7d…

plugin/skills/penthera/references/remediation.md

file

9,996 bytes

a8e243c34b25372b…

plugin/skills/penthera/references/reporting.md

file

5,515 bytes

4ac079a792d58cc8…

plugin/skills/penthera/references/secure-defaults.md

file

2,066 bytes

cc31ddbbb80ebab3…

plugin/skills/penthera/references/troubleshooting.md

file

2,889 bytes

232571a2b896c001…

plugin/skills/penthera/SKILL.md

skill

32,993 bytes

fd9b5e03d3f3882c…

README.md

file

35,992 bytes

019ec2a99dec2cf2…

SECURITY.md

file

2,566 bytes

9f3734ac4dbacf68…

skills/penthera/references/authorization.md

skill

2,511 bytes

91fa4d7ae933a130…

skills/penthera/references/output-and-ci.md

skill

3,242 bytes

c4f058a13c5b95d7…

skills/penthera/references/profiles-and-flags.md

skill

3,649 bytes

f1f8eee654d70c7d…

skills/penthera/references/remediation.md

skill

9,996 bytes

a8e243c34b25372b…

skills/penthera/references/reporting.md

skill

5,515 bytes

4ac079a792d58cc8…

skills/penthera/references/secure-defaults.md

skill

2,066 bytes

cc31ddbbb80ebab3…

skills/penthera/references/troubleshooting.md

skill

2,889 bytes

232571a2b896c001…

skills/penthera/scripts/preflight.sh

skill

2,781 bytes

7a27f6814c4a5619…

skills/penthera/scripts/validate-report.mjs

skill

1,448 bytes

064a61feaa7c5e7e…

skills/penthera/scripts/validate-report.sh

skill

307 bytes

e9c3d618a80d457b…

skills/penthera/SKILL.md

skill

32,993 bytes

fd9b5e03d3f3882c…

Penthera — Frequently asked questions

What is Penthera?
Penthera is an AI plugin in the HOL registry. The problem You ship faster than anyone can check your work. A coding agent writes the feature, you deploy, and nobody looked at the secrets in the repo, the new dependency, the headers, or the AI tool config that can run commands on your machine. How it works Penthera is…
How do I install Penthera?
Install Penthera in your harness: Claude Code — /plugin marketplace add danoszz/penthera; Antigravity CLI — npx [email protected] add danoszz/penthera; MCP — git clone https://github.com/danoszz/penthera. Full step-by-step guidance is on the HOL plugin page.
How do I install Penthera in HOL Guard?
To install Penthera in HOL Guard, start with hol-guard plugin install danoszz/penthera --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install Penthera in Claude Code?
To install Penthera in Claude Code, start with /plugin marketplace add danoszz/penthera. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install Penthera in Antigravity CLI?
To install Penthera in Antigravity CLI, start with npx [email protected] add danoszz/penthera. The complete step-by-step install guide for Antigravity CLI is on the HOL plugin page.
Is Penthera free?
Penthera is listed as free on HOL.
How is the Trust Score for Penthera computed?
Penthera has a HOL Trust Score of 85 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/danoszz%2Fpenthera/trust
Who publishes Penthera?
Penthera is published by danoszz and listed on HOL.
Is Penthera available now?
Penthera is currently available according to its latest public launch.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W46. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.
New GitHub stars
8
From HOL's GitHub snapshots of the repository, 2026-11-11 to 2026-11-19.

History, reviews, and similar plugins

Latest launch