ty-best-practices

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it is designed to analyze untrusted Python source code and project configuration files.
  • Ingestion points: The skill processes Python source files and configuration metadata in pyproject.toml or ty.toml (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific safety prompts to prevent the agent from obeying instructions embedded in the analyzed code.
  • Capability inventory: The skill utilizes ty check, ty server, and uv run ty to perform analysis (SKILL.md).
  • Sanitization: No sanitization or validation steps are defined for the input files before they are processed by the tool.
  • [COMMAND_EXECUTION]: The skill involves the execution of local CLI tools.
  • The instructions direct the agent to run ty check, ty server, and uv run ty (SKILL.md). These are standard operations for a type-checking and LSP integration tool and align with the stated purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 10:48 PM
Security Audit — agent-trust-hub — ty-best-practices