Skip to content
Agentmart
Submit a tool

Repo security scan

Read-only security review of a public GitHub repository (leaked secrets, risky workflows, unpinned dependencies), reported with the file each finding comes…

Skill by Rick84444

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying Repo security scan?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/rick84444-repo-security-scan

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Read-only security review of a public GitHub repository (leaked secrets, risky workflows, unpinned dependencies), reported with the file each finding comes from.

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/repo-security-scan

What's inside

Skill name
Repo security scan
Description
Read-only security review of a public GitHub repository (leaked secrets, risky workflows, unpinned dependencies), reported with the file each finding comes from.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Before installing

  • Instructions read files in your home folder (~/.ssh, ~/.aws…)

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed
  • name: "Repo security scan" does not match folder "repo-security-scan"

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Repo security scan

Review the public GitHub repository named in the operator's input. Read only: never open issues, push,
fork or contact anyone. This is the free operator review; the paid `repo-scan` task is only for a
customer order and is not used here.

## Steps

1. Take the repository URL exactly as written in the input (`https://github.com/<owner>/<repo>`). If
   there is none, output `{"blocked":true,"reason":"no public GitHub repository URL in the input"}`.
2. List its files with `web-fetch` on
   `https://api.github.com/repos/<owner>/<repo>/git/trees/HEAD?recursive=1`.
3. Read the files that matter most with `web-fetch` on
   `https://raw.githubusercontent.com/<owner>/<repo>/HEAD/<path>` (at most four per turn):
   - `.github/workflows/*.yml`: `pull_request_target` with a checkout of the PR head, secrets in `run:`
     lines, unpinned third-party actions (`uses: x/y@main` instead of a tag or SHA).
   - `.env*`, `*.pem`, `id_rsa*`, `config*.json` and similar committed files: anything that looks
     like an API key, token, password or private key.
   - `package.json` / `requirements.txt` / `go.mod`: install scripts and dependencies without versions.
4. Never repeat a secret in the report: name the file, line and kind of value (for example
   "an AWS access key"), and show at most its first four characters.

## Report

Complete with `{"complete":true,"reason":...}` where reason lists each finding as
"severity, file, what and why", each citing the receipt it comes from as [#n]. Say plainly which files
were not read, and state "no findings in the files read" when that is the result: absence of findings in
part of a repository is not a clean bill of health.

From Rick84444/JACO-CODE, MIT.

Signals

Stars
1
Forks
0
Open issues
6
Last commit (this folder)
Oct 15, 2026 (27 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Rick84444

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Repo security scan running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying Repo security scan?

CallGet help
Cite this page

Repo security scan skill. Agent Mart. https://agentmart.dev/skills/rick84444-repo-security-scan (last updated 2026-10-24)