cloud-monitoring-promql-query
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- Environment Access and Authentication: The skill uses commands to resolve project settings and generate authentication tokens within the user's environment. This is a standard method for agents to perform authorized operations on behalf of the user.
- Interaction with Official API Endpoints: The skill retrieves metric and resource descriptors directly from the official Cloud Monitoring API (monitoring.googleapis.com). These network operations are necessary for the skill's primary purpose and target well-known infrastructure.
- Dependency Management: The validation utility depends on the
promql-parserlibrary. The skill includes logic to ensure this dependency is installed, which is a common requirement for performing complex syntax validation of generated code. - Indirect Prompt Injection Surface: The skill converts natural language inputs into structured PromQL queries. Although this creates an entry point for potential indirect prompt injection, the skill implements a discovery protocol and a mandatory validation script that checks for syntax and semantic correctness.
Audit Metadata