marketplace-create-extension

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs filesystem operations to create directories and write files via Python's pathlib. This functionality is restricted to scaffolding the new project structure and is entirely consistent with the skill's stated infrastructure purpose.
  • [PROMPT_INJECTION]: The skill implements a template-based generation system that interpolates user inputs into generated documentation. While this creates a theoretical surface for indirect prompt injection within the created output files (e.g., injecting YAML fields into the generated SKILL.md), it does not affect the security of the agent executing the tool.
  • Ingestion points: Arguments name, description, author, and parent_dir in scripts/create_extension.py.
  • Boundary markers: Absent from the string templates used to generate SKILL.md and tools.yaml.
  • Capability inventory: File system write access via pathlib.Path.mkdir and pathlib.Path.write_text in scripts/create_extension.py.
  • Sanitization: Regular expression validation is applied to name and action_name to enforce kebab-case and snake_case respectively; other fields undergo basic whitespace stripping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:26 PM