The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists exclusively of Markdown files. There are no Python scripts, Node.js packages, shell scripts, or binary executables included in the package.\n- [DATA_EXPOSURE] (SAFE): No sensitive file paths, environment variable access, or hardcoded credentials (API keys, tokens) were identified in the documentation or templates.\n- [COMMAND_EXECUTION] (SAFE): The skill does not contain any instructions that would lead to the execution of system commands or subprocesses.\n- [REMOTE_CODE_EXECUTION] (SAFE): There are no patterns involving external downloads (curl, wget) or remote script execution.\n- [PROMPT_INJECTION] (SAFE): While the skill provides templates for prompts, it does not include instructions intended to bypass safety filters or override the agent's core system instructions for malicious purposes.

prompt-engineering