The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill makes HTTP requests to https://jaspar.elixir.no/api/v1/. This is the official public API for the JASPAR database, used for retrieving transcription factor binding profiles.
[COMMAND_EXECUTION]: The skill uses uv run to execute the local wrapper script scripts/jaspar_api.py. The script uses argparse for safe command-line argument parsing and urllib.parse.quote to sanitize user inputs used in URL construction.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API which is then processed by the agent. This represents an indirect prompt injection surface.
Ingestion points: Data is fetched in scripts/jaspar_api.py via _CLIENT.fetch_json and _CLIENT.fetch_text from the JASPAR API endpoints.
Boundary markers: No explicit boundary markers or instructions to ignore embedded content are used when presenting API results to the agent.
Capability inventory: The skill has network read capabilities via its Python script. It does not perform file writes or arbitrary shell execution beyond its own entry point.
Sanitization: Outgoing parameters are sanitized using urllib.parse.quote. Incoming data is not sanitized but is printed as formatted text or YAML, which is standard for bioinformatics data processing.

jaspar-database