The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to query the Context7 API and jq to parse JSON responses. This is the intended mechanism for searching and retrieving library documentation.
[EXTERNAL_DOWNLOADS]: The skill fetches text-based documentation from context7.com. These downloads are limited to documentation content and do not include executable scripts or binaries.
[PROMPT_INJECTION]: The skill processes external data, creating a potential surface for indirect prompt injection.
Ingestion points: Data enters the agent context through curl responses from the context7.com/api/v2/context endpoint.
Boundary markers: None; the retrieved documentation is processed directly by the agent without explicit delimiters or warnings to ignore embedded instructions.
Capability inventory: The skill uses curl and jq for network and data processing within SKILL.md.
Sanitization: There is no evidence of sanitization or filtering applied to the documentation content before it is read by the agent. While this is a standard surface for documentation-fetching tools, it is noted as a risk factor.

context7