The Agent Skills Directory

[SAFE]: No security issues detected across all analyzed files.
[COMMAND_EXECUTION]: The skill includes preprocessor.py and a helper shell script test_extractor.sh. These scripts are used for legitimate data processing tasks such as reading user-provided prompt files, cleaning text, and performing simple clustering. No dangerous or unauthorized command execution was found.
[DATA_EXFILTRATION]: There are no network-related commands (like curl or wget) or external API calls present in the skill's code. Data processing is restricted to local files provided by the user.
[REMOTE_CODE_EXECUTION]: The skill does not download external packages or execute remote scripts. The Python preprocessor uses only standard library modules.
[PROMPT_INJECTION]: The instructions in skill.md are focused on structured data extraction and analysis. They do not contain any patterns aimed at overriding agent safety guidelines or system prompts.

prompt-extractor