gcp-cicd-design
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
run_shell_commandas a fallback mechanism to executegcloudCLI commands when specialized tools are unavailable. This is part of its core functionality for managing GCP resources. - [PROMPT_INJECTION]: The agent performs autonomous context gathering by scanning local repository files such as
package.json,pom.xml, andrequirements.txt. This creates an indirect prompt injection surface where maliciously crafted files in a repository could influence the agent's behavior during the design phase. - Ingestion points: Reads files in the local repository (e.g.,
SKILL.md,references/how_to_build_cloudbuild_yaml.md). - Boundary markers: None explicitly defined for file reading operations.
- Capability inventory: Can execute shell commands (
run_shell_command), create GCP resources via Cloud Build, and use Terraform. - Sanitization: No explicit sanitization or validation of the contents of the scanned repository files is mentioned.
- [DATA_EXFILTRATION]: The skill gathers environmental data by running
gcloud config listandgit remote get-url origin. While intended for context gathering, this involves accessing local configuration metadata.
Audit Metadata