Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Auditing GitHub Actions workflows that run AI agents v1.0.0

Use this resource to audit GitHub Actions workflows that run AI agents

New

  • 481 downloads
  • 163 likes
  • 121 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install github-actions-ai-agent-audit-2

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent finds workflows and actions that invoke an AI agent, follows references into composite actions, then looks for attack vectors: third-party-controlled input, weak sandboxing and overly broad actor rules. It reports each finding with its evidence. You get an audit of CI chains to fix.

Mostly picked by

Updated November 2, 2026

Card for the “Auditing GitHub Actions workflows that run AI agents” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: six-step method, from analysis mode to reporting
  • references/: twelve files on attack vectors and action profiles

Good fit for

  • An AI review workflow reads PR comments
  • You add a coding agent to your CI and want to check it

Not for

    Tags

    • github actions
    • ai agents
    • injection
    • ci
    • audit

    About

    You say

    “Audit the GitHub Actions workflows in this repository that run an AI agent.”

    Card for the “Auditing GitHub Actions workflows that run AI agents” skill

    Skill published by waybarrios under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to audit GitHub Actions workflows that run AI agents
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/action-profiles.md8.8 KB
    • references/cross-file-resolution.md10.6 KB
    • references/foundations.md5.1 KB
    • references/vector-a-env-var-intermediary.md4.5 KB
    • references/vector-b-direct-expression-injection.md4.5 KB
    • references/vector-c-cli-data-fetch.md5 KB
    • references/vector-d-pr-target-checkout.md5.2 KB
    • references/vector-e-error-log-injection.md5.3 KB
    • references/vector-f-subshell-expansion.md5.7 KB
    • references/vector-g-eval-of-ai-output.md5.6 KB
    • references/vector-h-dangerous-sandbox-configs.md5.5 KB
    • references/vector-i-wildcard-allowlists.md4.4 KB
    • SKILL.md20.7 KB

    Origin and licence

    Listed unmodified

    Author
    waybarrios
    Source
    github.com/waybarrios/opencode-power-pack/tree/c3328ad1633c1561026532f29b718a2380bc52ee/skills/agentic-actions-auditor
    Licence
    MIT

    Notice

    « agentic-actions-auditor » (waybarrios, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.