auditing-cloud-cluster-security
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official CockroachDB command-line tools (
ccloud,cockroach sql) to retrieve cluster metadata and configuration. These interactions target official vendor infrastructure. - [SAFE]: Instructions explicitly mandate read-only operations, using
SHOWandSELECTSQL statements and non-modifying CLI subcommands (info,list,whoami) to prevent accidental or malicious state changes. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided input, such as cluster IDs and connection strings, which are interpolated into shell commands. While this represents a standard vulnerability surface, the context is limited to a structured security audit using established tools, and the instructions emphasize validation steps.
- [COMMAND_EXECUTION]: The skill executes shell commands using standard tools (
openssl,sslyze) and vendor-specific CLIs. These executions are necessary for the skill's primary function of assessing network and cryptographic posture.
Audit Metadata