The Agent Skills Directory

[PROMPT_INJECTION] (LOW): The skill processes user-supplied LaTeX files which could contain malicious instructions designed to influence the agent's output.
Ingestion points: extract_paper_elements.py reads user-provided .tex files and recursively resolves \input directives.
Boundary markers: Absent. Extracted content is not wrapped in delimiters to signal it as untrusted data to the LLM.
Capability inventory: The skill can read local files and write results to the file system.
Sanitization: Absent. There is no validation or sanitization of the LaTeX commands or extracted text.

slide-generation