gcp-playbooks
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a deterministic set of gcloud and kubectl commands for infrastructure discovery, project management, and incident mitigation (e.g., rollbacks and scaling), which align with the skill's stated SRE purpose.- [EXTERNAL_DOWNLOADS]: The included script
report_errors_by_revision.pyspecifies dependencies on established libraries such asgoogle-api-python-client,google-auth, andpython-dateutilfrom official registries.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its ingestion of error log data. - Ingestion points: The
report_errors_by_revision.pyscript retrieves error messages and stack traces from the GCP Error Reporting API. - Boundary markers: The script does not utilize specific delimiters or isolation markers when outputting the retrieved error messages to the agent context.
- Capability inventory: The skill has the capability to execute administrative shell commands and modify project configurations.
- Sanitization: Error messages are displayed without sanitization or validation of their content.
Audit Metadata