More screenshots
Works with the AI Agents you already use
🛡️ GitHub Actions Permission Hardener
Audit and harden GitHub Actions workflows against overbroad permissions, secrets exposure, and supply-chain risks.
$19
🛡️ GitHub Actions Permission Hardener
Example session with this skill installed
Audit my .github/workflows/deploy.yml file for security risks and suggest hardening steps.
- Read your context and instructions
- Compiled the github actions permission
Confirmed Findings
- High: Overbroad permissions.
permissions: write-alldetected. - Medium: Unpinned Action.
uses: actions/checkout@v2should use a SHA.
Fix
permissions:
contents: read
deployments: write
(Apply fix? [Y/N])
Connects securely to your tools. The creator never sees your data.
About this skill
Secure Your CI/CD Pipeline
GitHub Actions are the backbone of modern CI/CD, but misconfigured permissions can turn your automation into a security liability. This skill provides a specialized, evidence-first security audit and hardening workflow for your GitHub Actions YAML configurations.
What it does
The Permission Hardener goes beyond basic linting. It performs a deep heuristic scan of your workflow files to identify high-risk patterns that automated tools often miss. It evaluates:
- Permission Scoping: Identifies overbroad
GITHUB_TOKENpermissions and suggests least-privilege alternatives. - Supply Chain Security: Detects unpinned actions and unverified third-party scripts.
- Triggers & Injection: Flags unsafe
pull_request_targetusage and potential script injection points. - Resilience: Spots missing timeouts, concurrency conflicts, and cache poisoning risks.
Why use this skill
While generic AI prompts might give you vague advice, this skill uses a structured workflow involving local heuristic scripts and a specialized audit checklist. It ranks findings by severity (Critical to Info), provides exact evidence for every claim, and generates copy-paste remediation snippets that follow GitHub security best practices.
Output Format
Results are delivered in a developer-ready format including a scope of inspection, severity-ranked findings with cited evidence, and safe remediation templates. It clearly separates confirmed risks from hypotheses requiring manual verification.
- Does not change repository settings, branch protection, or GitHub secrets automatically.
- Heuristic scanner flags review targets; it does not prove the workflow is secure.
- Repository-level GitHub settings must be verified manually or with user-approved GitHub access.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 19 days ago
Requires
Permissions
File Scopes
Use read-only inspection first. The bundled scanner is a Python standard-library helper that reads matching files and prints markdown or JSON findings. It does not install dependencies, transmit data, call paid APIs, connect to live services, or modify files. Any write, install, deploy, payment, delete, reset, live-account action, or external network lookup requires explicit user confirmation.