The Agent Skills Directory

[SAFE]: The skill includes local Python scripts (init_agent.py, validate_agent.py) for scaffolding and validating agent files. These scripts perform safe local operations and do not access sensitive system files or network resources.\n- [SAFE]: YAML parsing within the validation script is performed using yaml.safe_load(), ensuring protection against YAML deserialization attacks.\n- [COMMAND_EXECUTION]: The skill executes its own internal Python scripts to perform structured tasks. This is restricted to the skill's local environment and provides deterministic validation results.\n- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the skill's instructions or supporting files.

create-agent