The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a local Python script scripts/passport.py to manage research data. Analysis of the script shows it only uses standard libraries (argparse, json, os, pathlib) to perform basic CRUD operations on JSON files without any dangerous subprocess calls or network activity.
[DATA_EXFILTRATION]: There are no network operations, API calls, or hardcoded secrets found in the code or instructions. The skill operates entirely on local project files.
[REMOTE_CODE_EXECUTION]: The skill does not download external scripts or packages. It relies solely on the provided Python scripts which are static and do not execute dynamic or remote code.
[PROMPT_INJECTION]: No patterns attempting to bypass safety filters or override system instructions were detected. The instructions are focused on structured research workflows.
[DYNAMIC_EXECUTION]: The Python scripts use standard JSON parsing and do not employ unsafe methods like eval(), exec(), or dynamic imports. File writing is handled safely using tempfile.mkstemp and os.replace to ensure data integrity.

rw-research-passport