manage-interface
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local Python script (
manage-interface.py) to perform its tasks. The script is invoked through a managed execution wrapper (.plan/execute-script.py). The script's logic is restricted to specific file operations and does not allow for arbitrary command execution. - [DATA_EXPOSURE]: File operations are strictly scoped to the
doc/interfaces/directory relative to the project root. The skill does not access sensitive system files, environment variables, or credentials. - [INDIRECT_PROMPT_INJECTION]: The skill includes a surface for ingesting user-supplied data (such as interface titles and content values) which are then stored in files. While these files are later read by the agent, the risk is mitigated by the fact that the skill's capabilities are limited to documentation management and do not include high-risk operations like code execution or network communication.
- [REMOTE_CODE_EXECUTION]: The skill does not download, fetch, or execute any external scripts or packages from the internet. All logic is contained within the provided local files and standard library imports.
Audit Metadata