truto-integrations-build

Fail

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation scripts from the vendor's dedicated domain at cli.truto.one. This is a legitimate setup step for the Truto command-line environment.
  • [REMOTE_CODE_EXECUTION]: Executes the downloaded vendor scripts by piping them directly to shell interpreters like bash and PowerShell's Invoke-Expression (iex). These actions are intended for CLI installation and originate from the author's infrastructure.
  • [COMMAND_EXECUTION]: Utilizes various CLI commands such as 'truto login', 'truto profiles', and 'truto integrations build' to manage credentials and perform integration scaffolding.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection (Category 8) because it utilizes an LLM-powered agentic loop to process external API documentation provided by users. * Ingestion points: The 'build' command fetches content from user-supplied URLs, and the agent uses 'web_search' and 'web_fetch' tools to gather additional context from the web. * Boundary markers: The provided documentation does not specify the use of clear delimiters or instructions for the agent to ignore embedded commands within the ingested data. * Capability inventory: The agent has the ability to generate and modify local configuration files and perform network operations via integrated tools. * Sanitization: No explicit sanitization or validation of the content retrieved from external documentation sites is documented.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.truto.one/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 21, 2026, 10:12 AM
Security Audit — agent-trust-hub — truto-integrations-build