openai-netlify-deploy
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve executing standard CLI tools via the
Bashtool. This includesnpx netlifyfor deployment tasks,npm installfor dependency management, andgitfor repository linking. These commands are consistent with the skill's stated purpose of automating Netlify deployments. - [EXTERNAL_DOWNLOADS]: The skill utilizes
npx netlifyto download and run the Netlify CLI, which is the official tool for a well-known service. It also facilitates project dependency installation vianpm. Both actions involve downloads from official registries. - [CREDENTIALS_UNSAFE]: The skill mentions authentication mechanisms like
NETLIFY_AUTH_TOKENandnpx netlify login. It provides secure guidance by instructing users to use placeholders for tokens and to manage secrets through the Netlify dashboard rather than committing them to version control. - [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading project configuration from external files to determine deployment settings.
- Ingestion points: Project configuration is read from
package.json,netlify.toml, and the output ofgit remote show origin(SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided when reading these files.
- Capability inventory: The skill uses the
Bashtool to execute shell commands and theWrite/Edittools to modify files. - Sanitization: Project configuration values are used as arguments for deployment commands without explicit sanitization steps defined in the skill.
- [DYNAMIC_EXECUTION]: The skill enables the execution of build scripts and plugins (e.g.,
@netlify/plugin-lighthouse) defined in the project's configuration files. This is a standard and expected feature of build and deployment automation.
Audit Metadata