wrdn-gha-workflows

wrdn-gha-workflows is a skill for Claude Code from getsentry/warden-skills. It costs 151 tokens per session (6,870 once invoked), scanned A, original, MIT.

A security review guide for finding exploitable GitHub Actions workflow bugs, where untrusted input can reach privileged code execution, credentials, repository writes, publishing, or deployment.

In plain words
What is it for?
Use it to review pull-request, comment, dispatch, and reusable workflows for command injection, unsafe checkouts, credential theft, and related CI security problems.
Why use it?
It focuses on proving the complete attack path across triggers, workflow files, reusable actions, permissions, and trust boundaries instead of flagging configuration patterns alone.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is - run: ./ci/deploy-preview.sh "${{ github.event.comment.body }}".

Good fit Use it to review pull-request, comment, dispatch, and reusable workflows for command injection, unsafe checkouts, credential theft, and related CI security problems.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/getsentry/warden-skills
agentmods
npx agentmods add skills/getsentry/warden-skills/wrdn-gha-workflows

Made for: Claude Code.

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 wrdn-gha-workflows

README.md
[![agentmods](https://agentmods.dev/badge/skills/getsentry/warden-skills/wrdn-gha-workflows/github.svg)](https://agentmods.dev/skills/getsentry/warden-skills/wrdn-gha-workflows)
Your own site
<a href="https://agentmods.dev/skills/getsentry/warden-skills/wrdn-gha-workflows"><img src="https://agentmods.dev/badge/skills/getsentry/warden-skills/wrdn-gha-workflows/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 wrdn-gha-workflows

Your own site · 80×15
<a href="https://agentmods.dev/skills/getsentry/warden-skills/wrdn-gha-workflows"><img src="https://agentmods.dev/badge/skills/getsentry/warden-skills/wrdn-gha-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,870 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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: 7 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 135
    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 Privilege Escalation · line 135
    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.
  • medium Rogue Agent · line 98
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium MCP Rug Pull · line 112
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 290
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 319
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Tool Misuse · line 135
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 $0.00151 $0.06870
Opus 5 $0.00076 $0.03435
Sonnet 5 $0.00030 $0.01374
Haiku 4.5 $0.00015 $0.00687

Measured 10d ago against content hash 3c408ae03abd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wrdn-gha-workflows scanned grade A 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 10d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import {execSync} from 'node:child_process';
skills/wrdn-gha-workflows/SKILL.md · 562 lines

How it starts

The opening of the file, as written. The whole thing — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior application security engineer. You hunt GitHub Actions bugs that let an external attacker, or a workflow caller with less privilege than the job, turn CI into code execution, credential theft, repository write access, package publication, or runner compromise.

This skill is exploit-oriented. It is not a YAML linter. A privileged trigger by itself is not a finding. A broad permissions: block by itself is usually not a finding. The finding is the chain: external or caller-controlled input reaches privileged execution, a trusted credential, or a trusted runner.

Trace. Do Not Skim.

GitHub Actions bugs hide across files. Read the workflow, follow every uses:, and prove the effective execution graph before reporting.

  • Start with the trigger. Identify whether an external attacker can start the workflow: fork PR, PR update, issue/PR/discussion comment, label event, workflow_run after untrusted work, or another public event. For workflow_dispatch and workflow_call, identify who can supply inputs and whether the job performs release, deploy, publish, signing, token, or runner-sensitive work.
  • Map trust boundaries. Separate base repository code from PR-controlled code, manual inputs, reusable workflow inputs, artifacts, caches, comments, titles, branch names, labels, and files loaded from the checked-out ref.
  • Follow call boundaries. Resolve local actions, composite actions, reusable workflows, and scripts called by run:. The dangerous behavior may sit in a callee while the privileged context is introduced by the caller.
  • Track token and secret scope. Read workflow- and job-level permissions:, secrets:, explicit PATs, deploy keys, OIDC credentials, package tokens, and checkout credential persistence.
  • Verify execution. Confirm attacker-controlled or caller-controlled code or text is interpreted by a shell, action, JS evaluator (actions/github-script), package lifecycle hook, script, config loader, cache restore, artifact consumer, or runner.
  • Use the shell. Use rg to find matching workflows, local actions, referenced scripts, reusable workflow calls, and sibling safe patterns. Use git log -p when a risky mitigation looks recently changed.

If you cannot trace the chain with the files available, either drop the finding or report it as medium confidence with the exact missing link. Do not report vague resemblance.

Read the full file on GitHub · 562 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. 10d ago First seen · 562 lines · 151 tokens per session scan A 3c408ae03abd

Subscribe to this mod's changes

wrdn-gha-workflows is a skill published in the GitHub repository getsentry/warden-skills (57 stars, last pushed 18d ago), licensed MIT. It adds 151 tokens to every session and 6,870 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

gha-security-review

GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks.…

getsentry/skills · 76 tokens

sentry-setup-releases

Set up Sentry releases and deploy tracking — tag events with a version and environment, create the release in CI with its commits, and wire up suspect commits and code mappings, so Sentry can show which release introduced an issue, which commit is responsible, and release health. Use when asked to set up releases…

getsentry/plugin-claude · 90 tokens

import-prom-rule

Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…

ccfos/nightingale · 125 tokens

chinese-git-workflow

A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.

jnMetaCode/superpowers-zh · 69 tokens

configure-env-variables

Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…

microsoft/power-platform-skills · 119 tokens

atmos-profiles

Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.

cloudposse/atmos · 35 tokens