jinko-context

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Python script scripts/manage_folders.py designed to be executed via the CLI. It uses the argparse module to handle user-supplied arguments for folder creation and parent ID specification. The execution is scoped to managing project organization within the Jinkō SDK environment.
  • [DATA_EXPOSURE]: The script scripts/manage_folders.py loads configuration from a .env file using python-dotenv. This is a standard and safe practice for managing API credentials and connection settings for the Jinkō SDK, ensuring secrets are not hardcoded in the source code.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where it ingests data from the Jinkō API (folder names and IDs) and processes user input for folder creation.
  • Ingestion points: Untrusted data enters the context via client.list_folders() and client.folder_tree() outputs in scripts/manage_folders.py.
  • Boundary markers: The instructions in SKILL.md provide clear guidance on terminology and response constraints, though they do not use explicit technical delimiters.
  • Capability inventory: The skill can list, create, and (per documentation in references/folder-management.md) update or delete folders via the Jinkō SDK.
  • Sanitization: The script performs a duplicate check in create_folder to prevent redundant organizational changes.
  • [REMOTE_CODE_EXECUTION]: The skill references the jinko-sdk (Jinkō Python SDK) as a dependency. References to external repositories and installation steps (e.g., novainsilico/jinko-skills) target the vendor's official resources, representing standard development workflow requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 03:28 PM