The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill performs legitimate network operations to fetch academic metadata from well-known scholarly infrastructure, including the CrossRef API, NCBI PubMed E-utilities, and the arXiv API.
[INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection as it ingests and processes untrusted data from academic search results.
Ingestion points: External content is retrieved via scripts/search_google_scholar.py, scripts/search_pubmed.py, and scripts/extract_metadata.py.
Boundary markers: The skill does not use specific delimiters but processes data through specialized scripts to extract structured metadata.
Capability inventory: The skill has access to Bash, Write, and Edit tools for performing searches and managing BibTeX files.
Sanitization: Data is sanitized using regular expression parsing and structured XML/JSON processing within the metadata extraction and formatting scripts.

citation-management