The Agent Skills Directory

[SAFE]: The skill interacts exclusively with the official and trusted ClinicalTrials.gov API (https://clinicaltrials.gov/api/v2). All network communication is restricted to this domain.\n- [COMMAND_EXECUTION]: The skill uses the uv tool to run a local Python script (scripts/clinical_trials_api.py). This script uses the argparse library to safely process command-line arguments and prevent command injection.\n- [DATA_EXFILTRATION]: There are no indicators of data exfiltration. The script only reads data from the specified API and writes it to a local file path provided by the user, without accessing sensitive system files or environment variables.\n- [PROMPT_INJECTION]: The SKILL.md instructions are focused on providing clear usage guidelines and do not contain any attempts to override model safety filters or system prompts.\n- [REMOTE_CODE_EXECUTION]: No patterns of remote code execution or untrusted dependency downloads were detected. The skill's dependencies are managed locally.

clinical-trials-database