skill-creator-yashu

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses RunCommand to execute local Python scripts (scripts/init_skill.py, scripts/quick_validate.py) to automate project setup and verify compliance with skill specifications.
  • [DYNAMIC_EXECUTION]: The scaffolding process involves generating new Python scripts (scripts/example.py) based on templates and user input to provide functional boilerplate for new projects.
  • [PRIVILEGE_ESCALATION]: The initialization utility sets executable permissions (0o755) on generated Python scripts to ensure they can be run immediately by the agent or user.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions as a generator that translates natural language user requirements into structured skill documentation and instructions.
  • Ingestion points: User requirements, functional descriptions, and triggers are ingested via the AskUserQuestion interaction.
  • Boundary markers: Not present; user input is interpolated directly into skill templates without explicit delimiters or "ignore instructions" warnings.
  • Capability inventory: The skill possesses capabilities for filesystem modification (Write, SearchReplace) and command execution (RunCommand).
  • Sanitization: Skill names are sanitized via regex to ensure valid kebab-case formatting, but descriptions and generated instructions are not filtered for malicious prompt content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:52 PM