validator-expert
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill uses a bash script to run gcloud commands. This is the intended functionality for a cloud validator.
- [DATA_EXPOSURE] (SAFE): No sensitive data is exfiltrated or exposed to the agent context. The script only returns status messages.
- [INDIRECT_PROMPT_INJECTION] (SAFE): The skill does not pass untrusted external data to the agent.
- Ingestion points: gcloud command output.
- Boundary markers: Not applicable as data is consumed by the shell script directly.
- Capability inventory: Bash tool access.
- Sanitization: The script processes raw data with grep and only outputs boolean-style status messages to the agent context.
Audit Metadata