The Agent Skills Directory

[SAFE] (SAFE): The skill and its associated Python script do not contain any malicious patterns. The code is transparent and performs only the described text-processing tasks.- [DATA_EXFILTRATION] (SAFE): No network activity was detected. The script only reads from and writes to the local file system as directed by the user.- [COMMAND_EXECUTION] (SAFE): The script does not utilize os.system, subprocess, or any other method to execute external commands.- [PROMPT_INJECTION] (SAFE): Although the script processes user-provided LaTeX files (Category 8 surface), it does not have any dangerous capabilities that could be exploited by malicious content within those files.
Ingestion points: extract_paper_elements.py reads the path provided via the --tex argument.
Boundary markers: No delimiters or specific 'ignore' instructions are used in the parsing logic.
Capability inventory: The script is limited to reading local files and writing the extracted results to a file.
Sanitization: The script enforces a .tex extension on recursively included files and truncates extracted text elements (e.g., sections, captions) to prevent excessive memory usage or overflow.

slide-generation