The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): The markdown files contain instructional content and best practices for API design. There are no attempts to override agent instructions, bypass safety filters, or extract system prompts.
[DATA_EXFILTRATION] (SAFE): No network operations (curl, wget, requests) or hardcoded credentials were detected. The Python script performs local file reads for analysis purposes only and does not transmit data externally.
[COMMAND_EXECUTION] (SAFE): The api_validator.py script uses static analysis (regex) to check for patterns in code. It does not use os.system, subprocess, or any other method to execute shell commands.
[EXTERNAL_DOWNLOADS] (SAFE): The skill does not define any external dependencies in requirements.txt or package.json, nor does it attempt to download code at runtime.
[DYNAMIC_EXECUTION] (SAFE): The script uses standard JSON parsing and regex. There is no usage of eval(), exec(), or unsafe deserialization (e.g., pickle).

api-patterns