Truto CLI
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides commands to install the Truto CLI by downloading scripts from the vendor's official domain (https://cli.truto.one/install.sh and https://cli.truto.one/install.ps1) and piping them into bash or PowerShell's Invoke-Expression. These are documented as the standard installation methods for the tool.
- [COMMAND_EXECUTION]: The skill involves the execution of the truto CLI for managing platform resources, which includes reading and writing to local configuration files such as ~/.truto/config.json.
- [DYNAMIC_EXECUTION]: The skill features truto jsonata eval and truto unified test-mapping commands which dynamically evaluate JSONata expressions against provided JSON data at runtime.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes data from external API responses.
- Ingestion points: Data returned by the Truto API via commands like unified, proxy, and custom are ingested into the agent's context (e.g., SKILL.md, references/querying-data.md).
- Boundary markers: No specific delimiters or instructions to treat tool output as untrusted are defined.
- Capability inventory: The skill allows the agent to execute shell commands and interact with the Truto platform via the CLI.
- Sanitization: No sanitization or validation of external data is specified.
Audit Metadata