The Agent Skills Directory

[SAFE]: The skill interacts with reputable academic services such as arXiv, Google Scholar, and Semantic Scholar, as well as the Zotero bibliographic platform. These interactions are consistent with its stated purpose and do not involve unauthorized access to sensitive user data or exfiltration to untrusted domains.
[PROMPT_INJECTION]: The skill is designed to process content from external research papers and web search results, which constitutes an indirect prompt injection surface as described in SKILL.md and references/zotero-integration-guide.md. However, given the context of analyzing peer-reviewed academic content from established databases, the risk is minimal. There are no explicit boundary markers or sanitization steps defined for the ingested data.
[EXTERNAL_DOWNLOADS]: The skill automates the retrieval of papers and metadata from well-known academic repositories and official registries such as CrossRef and Unpaywall. These activities are standard functionality for a research-oriented tool and do not involve execution of untrusted remote code.

research-ideation