The Agent Skills Directory

[SAFE]: The skill provides legitimate search functionality using public APIs from established legal information organizations including CourtListener, Harvard Law School, and the European Union.
[COMMAND_EXECUTION]: The skill employs curl and python3 for network requests and JSON data formatting. The commands use hardcoded local scripts for data processing and do not execute code from remote sources. Automated alerts regarding remote code execution are false positives in this context as the processing logic is static and the data sources are trusted.
[EXTERNAL_DOWNLOADS]: Fetches documents and metadata from well-known legal domains such as courtlistener.com, case.law, and eur-lex.europa.eu. These are appropriate and safe sources for the skill's stated purpose of legal research.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external legal APIs. It uses safe JSON deserialization and treats the retrieved content as reference text, posing no risk of instruction override or execution of data as code.

legal-search