dd-gcp-log-forwarding

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches modular instructional content from the vendor's official GitHub repository (github.com/datadog-labs/agent-skills) to support hand-offs between different setup phases.
  • [DATA_EXFILTRATION]: Performs network operations to official Datadog API endpoints (api.datadoghq.com and variants) to validate API and Application keys, and to Google Cloud APIs (cloudresourcemanager.googleapis.com) for resource discovery.
  • [COMMAND_EXECUTION]: Utilizes terraform (or tofu) and the gcloud CLI to provision infrastructure and discover GCP project metadata.
  • [INDIRECT_PROMPT_INJECTION]: Processes untrusted user input such as log filters and project IDs for interpolation into Terraform HCL files; the skill mitigates injection risks by providing explicit instructions for HCL-compliant character escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 10:13 PM