skills/gemini-cli-extensions/data-agent-kit-starter-pack/google-cloud-storage-fuse/Gen Agent Trust Hub
google-cloud-storage-fuse
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous instructions for executing
gcloud,kubectl, andgcsfusecommands to manage Cloud Storage buckets and GKE deployments. These include bucket creation, IAM binding management, and mounting operations. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs such as bucket names, project IDs, and cluster names, which are interpolated into shell commands. This represents a potential surface for indirect prompt injection, though the risk is minimized by the context of cloud infrastructure management.
- Ingestion points: User-supplied bucket names, project IDs, locations, and cluster names (e.g.,
gs://BUCKET,PROJECT_ID). - Boundary markers: None explicitly present for user-supplied strings interpolated into commands.
- Capability inventory: Execution of
gcloud,kubectl, andgcsfusevia the agent's shell environment. - Sanitization: None specified in the instructions.
- [EXTERNAL_DOWNLOADS]: The skill references official documentation and configuration files from the
GoogleCloudPlatformGitHub repository and Google Cloud's official documentation site. These are well-known, trusted sources.
Audit Metadata