google-cloud-filestore-auditing
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution via Subprocess: The skill utilizes the
gcloudCLI through the Pythonsubprocessmodule to interact with Google Cloud services. The commands are constructed using list-based arguments rather than shell strings, which is a standard and secure practice for cloud resource management tools. - External Resource References: The instructions reference official Google Cloud documentation for environment setup and interact with official GCP REST APIs. These references target trusted service domains and are necessary for the skill's intended functionality.
- Indirect Prompt Injection Surface: The skill ingests and analyzes configuration data from cloud instances. Because this data originates from the environment, it represents a standard surface for indirect prompt injection. The skill mitigates this by using structured JSON parsing in its audit script and rendering data into controlled markdown formats.
- Resource Modification Controls: The skill includes the ability to create backups, which can incur storage costs. This capability is managed by a mandatory confirmation gate, requiring the agent to obtain explicit user approval before executing any mutation commands.
Audit Metadata