SkillFoxx

Repo Forensics plugin

An offline scanner vets repositories, skills, plugins and MCP servers for malicious code before they reach your agent.

  • 205 ★ on the repository
  • Last commit
Plugin

Extended access

Why this level

  • Hooks intercept install commands and read code in scanned directories.
  • Without `--offline`, package names and versions go to external registries.
All reasons and checks

alexgreensh/repo-forensicsAuthor:alexgreensh

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add plugins/repo-forensics

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Hooks intercept install commands and read code in scanned directories.
  • Without `--offline`, package names and versions go to external registries.

This is third-party code. Review the repository files before installing.

What it does

Repo Forensics runs 29 scanners over a directory or repository: prompt injection, credential theft, supply chain, hidden Unicode, dependency confusion and other tricks. Correlation rules merge findings into one verdict with an exit code for CI, and results export to text, JSON or SARIF. Installed as a plugin, it watches the agent by itself. Hooks inspect `npm install`, `pip install` and `git clone` before and after they run, block known malicious packages and scan each new session. It needs no dependencies and sends no telemetry. Only package names and versions leave the machine for vulnerability lookups, and `--offline` switches that off too.

Who it is for. Developers and security teams who install third-party skills, plugins and MCP servers in Claude Code, Codex or Cursor.

Good fit when

  • Before installing an unfamiliar MCP server from a chat you want to know what it does.
  • A pull request brings a new GitHub Actions workflow and it must be reviewed before merge.
  • A team wants to block known malicious packages inside the agent session.
  • After a doubtful install you need to look for traces of supply chain attacks.

Not a fit when

  • You need a formal security audit of product code: the scanner looks for attacks on agents and does not replace a pentest.
  • The project is commercial: the license forbids commercial use without a separate agreement.
  • You want a full safety guarantee: a clean report only means no known indicators were found.

Example request

Scan ./suspicious-skill with repo-forensics and tell me whether it is safe to install.

Limitations

The license is PolyForm Noncommercial, with a separate small-business license for commercial use; read the terms in the repository. The scanner finds known indicators, so new or well-hidden code can slip through. It contacts registries and services for vulnerability lookups and signature checks unless `--offline` is set. Hooks intercept install commands in the session, which is barely noticeable but adds a step to each install. The last commit dates to November 2026.

How to disable. Remove the plugin with the client commands, for example `/plugin uninstall repo-forensics`; the hooks go with it.

FAQ

How do I install Repo Forensics in Claude Code?

Run `/plugin marketplace add alexgreensh/repo-forensics`, then `/plugin install repo-forensics@alexgreensh-repo-forensics`. Hooks attach on install.

Does my code go over the network?

No. Only package names and versions leave for vulnerability lookups and signature checks, and `--offline` disables those requests too.

What does a result look like?

A list of findings from critical to low and a verdict with an exit code. Code 2 means do not install. SARIF output fits the GitHub security tab.

Can I run it without the plugin?

Yes, Python 3.8 or newer is enough: clone the repository and run `./run_forensics.sh` on any folder.

Does it work with Codex and Cursor?

Yes. The repository ships plugin manifests for Codex, Cursor and Kimi Code, and auto-scan is listed for Claude Code and Codex.

Discussion

No questions or reviews yet.

Plugins

Security scanner for coding agents: checks code, MCP servers, prompts and model-invented packages, and gives an A to F grade.

MCP serverExtended access123

Security scanner for MCP servers that looks for hardcoded keys, tool poisoning and injection flaws in repository code.

CLIMinimal access139
Editors’ pick

A Snyk CLI that discovers installed MCP servers, skills and agents on your machine and checks them for prompt injections and malicious payloads

CLIExtended access3.2K
Editors’ pick

Security scanner for agent skills and MCP servers: finds prompt injection, data exfiltration and supply chain risks before install

CLIExtended access25.8K

A code security plugin: finds vulnerabilities, challenges its findings, proves exploitability and fixes with a verified patch

PluginBroad access121

README in short

The README explains the threats the scanners cover and shows sample output with a verdict. It continues with hooks, the scanner list, a section on trusting the tool itself and install steps.

README badge

Report a problem