cloudbase-cli

Pass

Audited by Gen Agent Trust Hub on Oct 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides comprehensive instructions for the agent to use the tcb CLI for managing cloud infrastructure. This includes powerful operations such as deleting cloud functions, clearing storage, and executing SQL mutations on MySQL instances.
  • Evidence: Found throughout all reference files, including tcb storage rm in references/storage.md and tcb db execute in references/mysql.md.
  • Mitigation: The skill's "Core Principles" mandate the use of --dry-run to preview destructive changes, environment verification via tcb env use, and checking official documentation via tcb docs and --help to ensure command accuracy.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local project files (e.g., cloudbaserc.json, package.json) and tool outputs (e.g., tcb docs, tcb logs) to automate deployments and verify configurations.
  • Ingestion points: The agent processes local development metadata and cloud service logs to inform its actions.
  • Boundary markers: The skill relies on structured data formats (JSON) and standard CLI output patterns rather than specific delimiters.
  • Capability inventory: The skill has the capability to perform wide-ranging cloud resource modifications based on the processed configuration.
  • Sanitization: No explicit sanitization of processed data is described, as the files are assumed to be part of the user's controlled development environment. This surface is characteristic of developer-focused tools and is mitigated by the skill's emphasis on user oversight.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 25, 2026, 09:53 AM