github-actions-security

github-actions-security is a skill for Claude Code, Codex from GoldenWing-360/claude-security-skills. It costs 80 tokens per session (2,636 once invoked), scanned B, original, MIT.

A security checklist for GitHub Actions, GitHub’s system for running automated jobs such as tests and deployments. It focuses on limiting what workflows can access and preventing outside code or input from being trusted by mistake.

In plain words
What is it for?
Use it when creating or auditing workflows, adding third-party actions, securing cloud deployments, investigating a leaked secret, or taking over a repository with unfamiliar automation.
Why use it?
An unsafe workflow can expose secrets, source code, or cloud accounts, especially when it uses changing third-party actions or runs code from a pull request. These practices reduce that exposure.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating or auditing workflows, adding third-party actions, securing cloud deployments, investigating a leaked secret, or taking over a repository with unfamiliar automation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goldenwing-360/claude-security-skills/github-actions-security
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add GoldenWing-360/claude-security-skills --skill github-actions-security
Clone the repo
git clone --depth 1 https://github.com/GoldenWing-360/claude-security-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for github-actions-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/github-actions-security.svg)](https://agentmods.dev/skills/goldenwing-360/claude-security-skills/github-actions-security)
Your own site
<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/github-actions-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/github-actions-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,636 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.02636
Opus 5 $0.00040 $0.01318
Sonnet 5 $0.00016 $0.00527
Haiku 4.5 $0.00008 $0.00264

Measured 8d ago against content hash 3a76776c3324, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

github-actions-security scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

GitHub Action expressions interpolate strings into shell scripts. Untrusted input that contains `; rm -rf /` becomes that, executed.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

github-actions-security/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Actions Security

GitHub Actions runs code with access to your secrets, your code, and increasingly your cloud accounts. Most teams ship workflows with the defaults, which are convenient but expose more than necessary. This skill is the working baseline for production-grade Actions usage.

When to invoke

  • Adding a new workflow
  • Introducing a third-party action (uses: someone/some-action@v1)
  • A workflow leaked a secret (cleanup + prevention)
  • Migrating from long-lived cloud credentials to OIDC
  • Periodic audit of .github/workflows/
  • Inheriting a repo with unfamiliar workflows

Rule 1 — Pin third-party actions to commit SHA

uses: someone/action@v1 looks safe. It's not. Tags and branches can be moved at any time. If the action's maintainer is compromised, every workflow using @v1 runs the new attacker code on next CI.

Pin to a commit SHA. Comment the version for readability:

# Bad
- uses: actions/checkout@v4

# Good
- uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1

For your own org / first-party actions, tag pinning is acceptable because you control the tag. For external actions: SHA pin.

dependabot can update SHA pins automatically — turn it on for .github/workflows/:

# .github/dependabot.yml
version: 2
updates:
  - package-ecosystem: github-actions
    directory: /
    schedule: { interval: weekly }

Rule 2 — Scope GITHUB_TOKEN permissions

GITHUB_TOKEN is created per workflow run. Its default permissions are broad — write to repo contents, issues, PRs, packages. Most workflows need read.

Set the floor at the workflow level, raise per-job only when needed:

name: CI

# Workflow-level default — read-only
permissions:
  contents: read

jobs:
  test:
    runs-on: ubuntu-latest
    # inherits read-only
    steps:
      - uses: actions/checkout@<sha>
      - run: npm test

  release:
    runs-on: ubuntu-latest
    needs: test
    # Raise only for this job
    permissions:
      contents: write           # for creating tags/releases
      packages: write           # for publishing
    steps:
      - uses: actions/checkout@<sha>
      - run: npm publish

Read the full file on GitHub · 251 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 251 lines · 80 tokens per session scan B 3a76776c3324

Subscribe to this mod's changes

github-actions-security is a skill published in the GitHub repository GoldenWing-360/claude-security-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,636 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

devops-engineer

Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing…

Jeffallan/claude-skills · 107 tokens

terraform-skill

Terraform infrastructure as code best practices.

Agent-Threat-Rule/agent-threat-rules · 10 tokens

review-tooling

Detect what dev tooling infrastructure a project has and flag gaps across linters, formatters, pre-commit hooks, test runners, and CI/CD pipelines. Returns structured findings without applying changes. Use when the user asks to "review tooling", "check project tooling", "what tooling is missing", "review dev…

tobihagemann/turbo · 74 tokens

Supply Chain Security

Software supply chain security — SBOM generation and analysis, dependency confusion and typosquatting detection, malicious package indicators, CI/CD pipeline hardening, and artifact provenance/signing (SLSA, Sigstore).

Masriyan/Claude-Code-CyberSecurity-Skill · 47 tokens

airflow-dag

Create Apache Airflow DAGs for construction data pipelines. Orchestrate ETL, validation, and reporting workflows.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 28 tokens

build-ci-migration-assistant

Automatically migrates build systems and CI/CD configurations to target platforms. Use when modernizing build infrastructure, switching CI/CD providers, or standardizing across projects. Supports common migration paths including Maven↔Gradle, npm↔Yarn, Travis CI→GitHub Actions, CircleCI→GitHub Actions, Jenkins→GitLab…

ArabelaTso/Skills-4-SE · 107 tokens