The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill performs network operations to api.exa.ai. Exa is a well-known search technology service, and these requests are the primary function of the skill for retrieving search results and page content.
[CREDENTIALS_UNSAFE]: The exa-api.cjs script manages the Exa API key by checking the EXA_API_KEY environment variable or reading from a local .env file. This is a standard and safe practice for secret management in development environments.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a local helper script (scripts/exa-api.cjs). The script is used to wrap API calls and process JSON payloads, which is consistent with the skill's stated architecture.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted data from external web searches and returns it to the agent context.
Ingestion points: Data enters the context via the exa-api.cjs script which fetches results from the Exa API.
Boundary markers: The skill returns results in structured JSON format, which provides a natural boundary, though no explicit instructions to ignore embedded content are provided in the prompt templates.
Capability inventory: The skill is configured with Bash and Read tool access.
Sanitization: The helper script performs JSON parsing of the API response but does not sanitize the text content retrieved from external web pages.

exa-search