skill-builder

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill utilizes the Bash tool to execute a suite of local Python scripts (e.g., validate_yaml.py, bulk_validate.py, interactive_editor.py) for skill management. This is necessary for the skill's primary function as a development wizard.
  • [PROMPT_INJECTION] (LOW): The skill acts as an ingestion surface for Indirect Prompt Injection (Category 8).
  • Ingestion points: User input collected via AskUserQuestion (e.g., skill name, description, author).
  • Boundary markers: Absent in the minimal-starter.md template used for scaffolding.
  • Capability inventory: Uses the Write tool to generate persistent files and the Bash tool to execute validation logic.
  • Sanitization: No explicit sanitization or escaping of user-provided metadata is performed before writing the generated SKILL.md file.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill does not perform any network operations or download code from external sources; all executed scripts are local to the skill directory or environment hooks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 07:20 AM