The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found. The skill uses natural instructional language for business strategy.
[DATA_EXFILTRATION] (SAFE): No hardcoded secrets, API keys, or sensitive local file path references were detected. There are no network operations (curl, wget, fetch) in any of the scripts.
[REMOTE_CODE_EXECUTION] (SAFE): The skill does not download or execute remote code. The scripts/validate.py script performs local directory and YAML file validation using standard Python libraries.
[COMMAND_EXECUTION] (SAFE): No use of dangerous subprocess calls, os.system, or shell execution was found. File system operations are limited to reading local configuration files.
[DYNAMIC_EXECUTION] (SAFE): No use of eval(), exec(), or unsafe deserialization (e.g., pickle) was detected. The YAML loader uses safe_load.

pricing