The Agent Skills Directory

[SAFE]: The skill interacts with well-known and reputable academic services including the arXiv API, Semantic Scholar API, Unpaywall, CORE.ac.uk, and PubMed Central to retrieve research metadata and documents.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external PDF files, which is an inherent risk when ingesting untrusted data.
Ingestion points: External PDF documents retrieved from academic repositories or author preprint pages.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the converted paper content.
Capability inventory: Uses the convert_to_markdown tool and standard reading tools to process file content.
Sanitization: There is no mention of sanitizing or validating the content of the PDF before extraction of key findings and methodology.

papers