The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The Python scripts perform standard file system operations (reading, writing, and zipping files) necessary for packaging. No arbitrary shell command execution or subprocess spawning with untrusted input was found.
[DATA_EXFILTRATION] (SAFE): There are no network operations, curl/wget commands, or patterns indicating the unauthorized transmission of data to external sources.
[PROMPT_INJECTION] (SAFE): The documentation files (references/) provide templates for high-quality outputs and workflows. These are instructional guides for the agent and do not contain bypass markers, override instructions, or jailbreak attempts.
[EXTERNAL_DOWNLOADS] (SAFE): The scripts do not perform any remote downloads or runtime package installations.
[REMOTE_CODE_EXECUTION] (SAFE): No patterns for dynamic code execution (e.g., eval, exec) or remote script execution were detected.
[DYNAMIC_EXECUTION] (SAFE): The validation script correctly uses yaml.safe_load() to parse frontmatter, preventing unsafe deserialization vulnerabilities.

skill-creator