bk-cli-paas
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill defines specific usage patterns for the
bk-clicommand-line tool. It instructs the agent on how to construct commands likebk-cli paas get_deployment_resultandbk-cli paas deploy_with_moduleusing arguments provided via CLI flags. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data (such as app codes, module names, and deployment IDs) and interpolates them into shell commands. While this creates a potential attack surface for indirect prompt injection or command argument manipulation from untrusted inputs, the skill assumes a controlled environment where the agent uses the
bk-clitool as intended by the vendor. - [SAFE]: The skill references a local shared resource
../bk-cli-shared/SKILL.mdfor authentication and global settings, which is a standard practice for modular skill development and does not involve remote code execution or unauthorized access.
Audit Metadata