Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills Aโ€“Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

honeybadger

ASecurity

Scan a GitHub or GitLab repository for security issues before installing it as a skill, tool, or MCP server. Use when the user wants to check, vet, scan, or review a repository for safety before installation. Detects hardcoded secrets, known CVEs, supply chain risks, and build provenance.

3 stars
0 votes
0 copies
0 views
Added 10/6/2026
securitygoshellbashgitsecurity

Works with

mcp

Security Analysis

A100/100

Pro scans all 18 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add famclaw/honeybadger --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of honeybadger?

Add the live security badge to your README โ€” it updates automatically with every re-scan.

Security grade badge for honeybadger
[![Security: A โ€” Skills Directory](https://www.skillsdirectory.com/api/skills/famclaw-honeybadger/badge)](https://www.skillsdirectory.com/skills/famclaw-honeybadger)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: honeybadger
version: "1.0.0"
description: >
  Scan a GitHub or GitLab repository for security issues before installing it
  as a skill, tool, or MCP server. Use when the user wants to check, vet,
  scan, or review a repository for safety before installation. Detects
  hardcoded secrets, known CVEs, supply chain risks, and build provenance.
author: famclaw
license: MIT
tags:
  - security
  - scanner
  - supply-chain
  - mcp
metadata: {
  "openclaw": {
    "emoji": "๐Ÿฆก",
    "requires": { "bins": ["honeybadger"] },
    "install": [
      {
        "id": "go-install",
        "kind": "shell",
        "command": "go install github.com/famclaw/honeybadger/cmd/honeybadger@latest",
        "bins": ["honeybadger"],
        "label": "Install HoneyBadger (requires Go)"
      }
    ]
  }
}
---

# HoneyBadger

HoneyBadger is a security scanner for software plugins. Before anything gets
installed on your family server or development machine, HoneyBadger checks it.

**HoneyBadger don't care. HoneyBadger checks anyway.**

## When to use this skill

Use this skill when the user:
- Wants to install a skill, MCP server, or tool from a GitHub or GitLab repo
- Asks "is this safe to install?", "can you check this?", "vet this repo"
- Wants to verify an update to an already-installed skill
- Asks about the security of any GitHub or GitLab repository

## Prerequisites

The `honeybadger` binary must be in PATH. If not installed:

```bash
go install github.com/famclaw/honeybadger/cmd/honeybadger@latest
```

## How to invoke

Basic scan (default: family paranoia level):
```bash
honeybadger scan <repo-url> --format text
```

With specific paranoia level:
```bash
honeybadger scan <repo-url> --paranoia minimal|family|strict|paranoid --format text
```

For update verification (rug-pull detection):
```bash
honeybadger scan <repo-url> --installed-sha <sha256-of-installed-archive>
```

## Paranoia levels

- **minimal** โ€” secrets + CVEs only. Fast. No LLM. Blocks on CRITICAL.
- **family** โ€” full scan + LLM verdict. Default. Blocks on HIGH+.
- **strict** โ€” adds attestation + build provenance. WARN treated as FAIL.
- **paranoid** โ€” strict + allowlist enforcement. Blocks on LOW+.

## How to interpret output

Exit codes: 0=PASS, 1=WARN, 2=FAIL, 3=scan error

With `--format text`: human-readable summary.
With `--format ndjson`: one JSON event per line. The final line
(`"type":"result"`) contains the verdict and reasoning.

Always show the verdict and reasoning to the user.
If verdict is WARN or FAIL, quote the `key_finding` field.
If verdict is FAIL, tell the user not to install.

## Example

User: "Is github.com/some-user/some-skill safe to install?"

```bash
honeybadger scan github.com/some-user/some-skill --format text
```

Report the verdict and reasoning to the user in plain language.

Attribution

famclawfamclaw
View sourceSee grades on GitHubMore from famclaw โ†’
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Security Review

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

2456590 votes

Springboot Security

Java Spring Boot ๆœๅŠกไธญๅ…ณไบŽ่บซไปฝ้ชŒ่ฏ/ๆŽˆๆƒใ€้ชŒ่ฏใ€CSRFใ€ๅฏ†้’ฅใ€ๆ ‡ๅคดใ€้€Ÿ็އ้™ๅˆถๅ’Œไพ่ต–ๅฎ‰ๅ…จ็š„ Spring Security ๆœ€ไฝณๅฎž่ทตใ€‚

2456590 votes

Summarize Status

Write a short, colloquial summary for a Paperclip summary slot: open with the 1โ€“3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.

953190 votes

Paperclip Task Bridge

Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.

953190 votes

Paperclip Evals

Choose, inspect, validate, and report Paperclip Runner or Product E2E evaluations while preserving evidence, provenance, cost, and failure classification.

953190 votes
View all in security โ†’