make-github-actions-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Security Guidance for Privileged Contexts: The skill provides explicit instructions to avoid checking out or executing code from pull request forks when using the
pull_request_targettrigger. This is an important security measure to prevent unauthorized access to repository secrets or internal systems by external contributors. - Principle of Least Privilege: The instructions require the declaration of explicit, minimal permissions for every workflow. This follows the security best practice of ensuring that automated processes only have the access necessary to perform their specific tasks, reducing the potential impact of a workflow compromise.
- Indirect Prompt Injection Surface: The skill is designed to ingest external data, such as pull request payloads and repository file contents, to generate or update workflows. While processing untrusted data provides a surface for indirect prompt injection, the skill includes guard conditions and validation steps intended to keep the generated output within repository conventions.
- Use of Standard Tooling: The skill recommends using
actions/github-script, a well-known and widely-used GitHub Action, for complex logic. This encourages a consistent and observable scripting environment compared to arbitrary shell scripts.
Audit Metadata