skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides an initialization script (init_skill.py) and instructions for the agent to use shell commands such as chmod and ln to configure skill directories and link them to the agent's command path.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) because it uses user-provided names and descriptions to generate file content and directory paths.
  • Ingestion points: User input passed as arguments to init_skill.py and content written to SKILL.md.
  • Boundary markers: Absent; user strings are interpolated directly into templates without explicit delimiters.
  • Capability inventory: The skill utilizes file system capabilities including directory creation, file writing, permission modification, and symlink creation.
  • Sanitization: Absent; the initialization script does not rigorously sanitize the skill name argument, which is a common pattern for local developer tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:40 AM