skills/googlecloudplatform/data-agent-kit-plugin/gcp-pipeline-resource-provisioning/Gen Agent Trust Hub
gcp-pipeline-resource-provisioning
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
gcloudandgitcommand-line tools to discover environment parameters, such as Project ID and Region, and to perform the deployment of infrastructure resources. These commands are necessary for the skill's primary function of cloud resource management. - [INDIRECT_PROMPT_INJECTION]: The skill generates and updates a
deployment.yamlfile used for resource provisioning, which introduces a surface for indirect prompt injection where configuration data could potentially influence the execution flow. - Ingestion points: The
deployment.yamlconfiguration file (SKILL.md). - Boundary markers: The skill does not define specific delimiters to separate data from instructions within the YAML file, though it uses standard templating syntax.
- Capability inventory: The skill can execute shell commands via
gcloud beta orchestration-pipelines deployandgcloud beta orchestration-pipelines validate(SKILL.md). - Sanitization: A required validation step (
gcloud beta orchestration-pipelines validate) is implemented to check the syntax and variable resolution before deployment (SKILL.md).
Audit Metadata