cerberus
v2.1.4CERBERUS — the two-headed guard at the gate for a PUBLIC skills marketplace. A PostToolUse hook fires on every skill / reference / script / eval / manifest edit and reminds you to run BOTH heads before committing: cerberus:leak-check (outward — no real work identifier or secret escapes into the public marketplace) and cerberus:security-scan (inward — the eight-point consumer-safety checklist: prompt injection, exfiltration, secrets, dangerous commands, obfuscation, external fetches, credential access, privilege escalation, so nothing unsafe reaches whoever installs the skill). Both are agent judgment passes, no denylist by design — a list of the real names to catch would itself be the leak; the intelligence lives in the agent, not a regex.
By Roman Maslennikov1 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 1 skill or MCP entry
- Source updated
- Oct 6, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install cerberus for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install cerberus@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/aquivalabs/BladeForgeClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/cerberus/.
Plugin files
├── .claude-plugin/plugin.json└── skills/leak-check/SKILL.md
Included Skills1
Use before committing a NEW or EDITED skill, its references, its bundled scripts, or its eval fixtures to this PUBLIC marketplace — review the change for anything that points to a real work codebase (real class/object/namespace/org/ticket names, secrets, real people/emails/paths, an employer or client brand, or the aggregate "this is one specific company's product" flavor) and rewrite it to a neutral fictional demo before it ships. Also runs when the CERBERUS hook flags a skill/script/eval edit.
Plugin manifests1
{
"name": "cerberus",
"description": "CERBERUS — the two-headed guard at the gate for a PUBLIC skills marketplace. A PostToolUse hook fires on every skill / reference / script / eval / manifest edit and reminds you to run BOTH heads before committing: cerberus:leak-check (outward — no real work identifier or secret escapes into the public marketplace) and cerberus:security-scan (inward — the eight-point consumer-safety checklist: prompt injection, exfiltration, secrets, dangerous commands, obfuscation, external fetches, credential access, privilege escalation, so nothing unsafe reaches whoever installs the skill). Both are agent judgment passes, no denylist by design — a list of the real names to catch would itself be the leak; the intelligence lives in the agent, not a regex.",
"version": "2.1.4",
"keywords": [
"security",
"leak-guard",
"secret-scan",
"fingerprint",
"hook",
"pre-commit"
],
"author": {
"name": "Roman Maslennikov",
"email": "[email protected]"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[cerberus on Agent Plugins Marketplace](https://pluginsmp.com/plugins/cerberus)