iam-recommendations-fetcher

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution: The skill utilizes the gcloud command-line interface to interact with Google Cloud services. Specifically, it uses gcloud recommender and gcloud projects list to fetch security insights and resolve resource identifiers. These operations are restricted to the target scope specified by the user and are necessary for the skill's primary function of retrieving administrative data.
  • Data Retrieval and File Operations: The skill retrieves IAM recommendation data and presents it to the user. It offers the option to save this data into local JSON or Markdown files. These file operations are conducted within the current working directory and are used to provide the user with a persistent record of the security recommendations.
  • Input Validation and Error Handling: The skill includes detailed instructions for validating target resource identifiers (Organization, Folder, Project) before any API calls are made. It also defines strict error-handling paths that terminate execution upon encountering authorization or resource-existence errors, which helps prevent unnecessary or unauthorized access attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 06:10 PM
Security Audit — agent-trust-hub — iam-recommendations-fetcher