The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to interact with an external API and jq to parse the resulting JSON output. These commands are integral to the skill's documented workflow.
[EXTERNAL_DOWNLOADS]: The skill fetches software library documentation and search results from the context7.com API. This is the primary function of the skill.
[DATA_EXFILTRATION]: Search queries and library identifiers are transmitted to context7.com via HTTP GET requests. While this is necessary for functionality, it involves sending user-supplied parameters to an external service.
[PROMPT_INJECTION]: The skill ingests technical documentation from an external source, creating a surface for indirect prompt injection.
Ingestion points: Documentation content is fetched from https://context7.com/api/v2/context (SKILL.md).
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when the agent processes the fetched data.
Capability inventory: The skill utilizes curl for network operations and jq for data processing (SKILL.md).
Sanitization: The skill recommends URL-encoding parameters for request formatting, but no sanitization is performed on the content retrieved from the API.

context7