desktop-plugins-tauri
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: Documents building applications that ingest external data, creating a potential surface for indirect prompt injection. * Ingestion points: Data entry from the file system (examples/data-storage.md), network responses (examples/networking.md), and SQL queries (examples/data-storage.md). * Boundary markers: Instructions do not cover using delimiters to isolate untrusted content. * Capability inventory: High-privilege operations including shell command execution via tauri-plugin-shell (examples/system.md), file system writes via tauri-plugin-fs (examples/data-storage.md), and networking (examples/networking.md). * Sanitization: Recommends scoped permissions in capability files (SKILL.md) and argument validators for shell commands (examples/system.md).
- [COMMAND_EXECUTION]: Instructions for the tauri-plugin-shell plugin enable executing system commands. Although the documentation promotes security best practices, the capability is high-risk.
- [EXTERNAL_DOWNLOADS]: Facilitates installation of Tauri 2.x plugins via cargo add and npm install from the official @tauri-apps and tauri-plugin namespaces.
Audit Metadata