cloud-monitoring-list-time-series-request
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution Capability: The skill instructs the agent to perform environment checks (e.g., using
gcloud) and to validate requests via direct API calls if specific tools are unavailable. This behavior is consistent with the skill's purpose of automating Cloud Monitoring tasks. - Indirect Prompt Injection Surface: The skill ingests and processes external metric descriptors to construct query filters.
- Ingestion points: External metric metadata is retrieved via the
list_metric_descriptorstool or direct API responses. - Boundary markers: The skill provides a structured JSON template for request construction, which helps define boundaries for external data.
- Capability inventory: The skill utilizes monitoring API tools and may execute shell commands for project identification or API interaction.
- Sanitization: The instructions focus on structural validity; standard platform-level sanitization for API inputs is expected.
Audit Metadata