ty-skills

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (HIGH): The skill instructs users to install a package named 'ty' via pip or uv, while falsely claiming it is an official tool by Astral and providing dead links to astral.sh. This is a classic supply-chain attack vector.
  • [REMOTE_CODE_EXECUTION] (HIGH): Encourages execution of ty check and ty server. Since the source is misrepresented, this involves running code from an unverifiable and potentially malicious source.
  • [COMMAND_EXECUTION] (HIGH): The skill relies on system-level command execution to perform its primary function, which becomes dangerous when the underlying tool's integrity cannot be verified.
  • [PROMPT_INJECTION] (LOW): The skill creates a surface for Indirect Prompt Injection as it processes workspace code without sanitization or boundary markers. 1. Ingestion point: Workspace code files processed by 'ty check'. 2. Capability: System command execution and file reading. 3. Boundaries: Absent. 4. Sanitization: None.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:11 PM