tauri-security-rules

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file contains a 'Memory Protocol' section that instructs the agent to run cat .claude/context/memory/learnings.md. This is a standard mechanism for maintaining stateful context across interactions and is not used for malicious exfiltration in this context.\n- [PROMPT_INJECTION]: The skill processes untrusted user code files, which is an inherent vulnerability surface for indirect prompt injection.\n
  • Ingestion points: User-provided source code files accessed via globs src/**/*.{svelte,ts,tsx}.\n
  • Boundary markers: Absent; the skill does not define specific delimiters for user-provided code.\n
  • Capability inventory: Access to Read, Write, and Edit tools, and command execution via cat.\n
  • Sanitization: No explicit sanitization or filtering of the code content is specified.\n- [SAFE]: The core instructions focus on enhancing security for Tauri applications, specifically recommending HTTPS, input validation, and careful management of the Tauri IPC allowlist.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 01:04 AM