The Agent Skills Directory

[SAFE]: The skill provides a structured methodology for academic research and includes utility scripts (scripts/citation_formatter.py and scripts/search_analyzer.py) that use standard Python libraries for data processing without dangerous operations.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill uses WebFetch to interact with the CrossRef API (api.crossref.org) for mandatory citation verification as specified in SKILL.md. CrossRef is a well-known and trusted academic service, and this interaction is consistent with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize information from external academic databases and search results. While this constitutes an attack surface, it is the primary functional requirement of the skill. The provided documentation in SKILL.md emphasizes strict metadata verification to prevent hallucination, and the processing logic in the provided scripts does not involve the execution of untrusted data.

literature-review