val-town-cli
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [Command Execution] (SAFE): The skill is primarily a reference for executing
vtCLI commands to manage serverless functions. These operations are the intended primary purpose. - [Indirect Prompt Injection] (LOW): The skill possesses an attack surface where untrusted data could influence agent behavior.
- Ingestion points: Remote logs via
vt tail, external code viavt cloneorvt pull, and environment configurations. - Boundary markers: None identified. Instructions do not include delimiters or warnings to ignore embedded commands in logs or code files.
- Capability inventory: Full access to the
vtCLI which can push, pull, delete, and modify remote infrastructure. - Sanitization: No evidence of output sanitization or validation of the data retrieved from Val Town servers.
- [Best Practice Violation] (LOW): The skill explicitly documents how to disable safety confirmations via
vt config set dangerousOperations.confirmation false. While a legitimate CLI feature, recommending its use to an AI agent increases the risk of unintended destructive actions.
Audit Metadata