gcp-resource-optimizer
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the gcloud CLI to perform various administrative tasks such as describing billing accounts, listing unused resources (disks, IP addresses, snapshots), and creating budget alerts. These commands are integral to the skill's purpose of resource optimization.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it incorporates user-supplied identifiers directly into shell commands.
- Ingestion points: Project and billing account ID placeholders in SKILL.md.
- Boundary markers: Absent; no delimiters or instructions to ignore embedded instructions are provided.
- Capability inventory: Shell execution of gcloud commands (e.g., gcloud billing accounts describe).
- Sanitization: Absent; input identifiers are used directly without validation or escaping.
- [SAFE]: No obfuscation, hardcoded credentials, or unauthorized network operations were identified. The skill behavior is transparent and consistent with its documentation.
Audit Metadata