The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to search and extract content from the public web, which constitutes a surface for indirect prompt injection attacks.
Ingestion points: Data enters the agent context through search results, direct content extraction, and research reports fetched from the api.exa.ai endpoints.
Boundary markers: The provided instructions do not specify explicit delimiters or 'ignore embedded instructions' warnings for the data returned by the API.
Capability inventory: The skill utilizes curl and jq to interact with the API and process data.
Sanitization: There is no evidence of sanitization or filtering of the external web content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill instructs the agent to use standard system utilities (curl, jq) for API interaction and configuration management.
The shell commands are used to read and write a local configuration file at ~/.config/exa-search/config.json and to perform HTTP requests to the legitimate api.exa.ai service.
These operations are consistent with the skill's stated purpose and do not involve arbitrary code execution or unsafe user input interpolation.

exa-search