The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes local Python scripts to interface with the Exa API. These commands are limited to the skill's defined functionality.
[EXTERNAL_DOWNLOADS]: The skill requires the exa-py SDK and python-dotenv, which are downloaded from official package registries. These are standard dependencies for integrating with the Exa search service.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted content from external websites.
Ingestion points: Web content and search results are ingested through the scripts/exa_search.py and scripts/exa_extract.py scripts via the Exa API.
Boundary markers: The reference files provide instructions for the agent on how to cite and structure output, but they do not use explicit delimiters to isolate external content from agent instructions.
Capability inventory: The skill includes file-writing capabilities to save search results locally, but it does not execute the content it fetches.
Sanitization: The Python scripts utilize standard JSON serialization to process external data, ensuring it is handled as data rather than executable code.

exa-search