Repo Forensics — Security Audit for Repos, AI Skills & MCP

Runs 27 scanners over a git repo, AI skill, or MCP server to surface prompt injection, credential theft, supply-chain tampering, and actively exploited CVEs.

Security & ReviewIntermediate★ 158⑂ 24AI score 10/10Last updated: Aug 20, 2026

What it does

Executes 27 scanners plus correlation rules against a git repository, a Claude Code skill/plugin, or an MCP server and produces a severity-ranked report.
Detects prompt injection, invisible Unicode smuggling, credential/env exfiltration, install-time lifecycle scripts, typosquats and known-compromised package versions, post-install behavior change (dynamic imports, time bombs), manifest drift, payloads hidden in archives or .pyc bytecode, and claimable dead links (skilljacking).
Enriches dependency findings from OSV and the CISA KEV catalog, escalating actively exploited CVEs to CRITICAL.
Supports text/JSON/SARIF output with deterministic exit codes (0/1/2) for CI gating, plus an --offline mode that relies only on the shipped rule packs.

Who it's for

Anyone who wants to vet a third-party Claude Code skill, plugin, or MCP server before installing it.
Developers reviewing a new open-source dependency before adding it to a project.
Security engineers investigating a suspected supply-chain compromise or wiring a security gate into CI.

Examples

./scripts/run_forensics.sh ./new-skill --skill-scan — fast pass over a freshly downloaded AI skill looking for prompt injection and backdoors.
./scripts/run_forensics.sh . --format json — full-repo audit as JSON, then fail the CI build on HIGH/CRITICAL findings.
./scripts/run_forensics.sh ~/project --update-vulns — refresh KEV/OSV feeds and flag pinned lockfile versions with exploited CVEs.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alexgreensh/repo-forensics/HEAD/plugins/repo-forensics/skills/repo-forensics/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the plugins/repo-forensics/skills/repo-forensics folder from the GitHub repo alexgreensh/repo-forensics into my ~/.claude/skills/repo-forensics/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alexgreensh/repo-forensics.git && mkdir -p ~/.claude/skills && cp -r repo-forensics/plugins/repo-forensics/skills/repo-forensics ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal and go to a working directory.
Clone the repo: git clone https://github.com/alexgreensh/repo-forensics.git
Create the skills directory: mkdir -p ~/.claude/skills
Copy the skill in: cp -r repo-forensics/plugins/repo-forensics/skills/repo-forensics ~/.claude/skills/
Make the scripts executable: chmod +x ~/.claude/skills/repo-forensics/scripts/*.sh
Confirm Python 3 is available (python3 --version). Optionally pip install yara-python to enable the YARA scanner.
Restart Claude Code, then ask "audit this repo for security issues" or invoke /repo-forensics <path>.
On the first run, triage CRITICAL/HIGH findings first — LOW items are informational and may be false positives.

View source on GitHub ↗License: NOASSERTION