The Agent Skills Directory

[SAFE]: No malicious code or suspicious behavior was identified in the logic or metadata of the skill. \n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external document content to influence its restructuring and formatting logic. \n
Ingestion points: Document content is ingested in formatter.py via the read_docx and read_text functions. \n
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing flow. \n
Capability inventory: The skill has the capability to write files to disk (doc.save) and execute shell commands (libreoffice via subprocess.run). \n
Sanitization: No evidence of content validation or sanitization was found before the document content is used in restructuring tasks. \n- [COMMAND_EXECUTION]: The formatter.py script uses subprocess.run to invoke libreoffice for PDF conversion. This operation is implemented safely using a list of arguments, which prevents shell command injection.

word-formatter