google-cloud-storage-fuse
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides standard command-line instructions using official tools such as
gcloud,kubectl, andgcsfuse. These commands are used for bucket management, IAM policy binding, and filesystem mounting. - [EXTERNAL_DOWNLOADS]: The skill references external documentation and source code from trusted domains including
cloud.google.comand the official Google Cloud Platform GitHub repository (github.com/GoogleCloudPlatform/gcsfuse). These references are used for technical background and configuration guidance. - [DATA_EXPOSURE_EXFILTRATION]: No hardcoded credentials or sensitive data exposure was detected. The skill uses clearly marked placeholders (e.g.,
PROJECT_ID,BUCKET,KSA_NAME) for user-specific environment variables. It also implements usage attribution via standard Google Cloud SDK environment variables (CLOUDSDK_METRICS_ENVIRONMENT) and User-Agent headers, which are documented as containing no user data. - [INDIRECT_PROMPT_INJECTION]: The skill functions as a configuration generator, ingesting user-provided infrastructure details to produce Kubernetes manifests and shell commands. This is the primary intended purpose of the skill and does not present an unusual attack surface.
Audit Metadata