The Agent Skills Directory

[SAFE]: The skill provides legitimate functionality for resolving library IDs and querying documentation via the Context7 service. Analysis of the instructions confirms there are no instances of credential exfiltration, remote code execution, or unauthorized command execution.
[INDIRECT_PROMPT_INJECTION]: The skill ingests documentation from an external service, creating a surface for indirect prompt injection. Ingestion points: Content is retrieved using the query-docs tool as described in SKILL.md. Boundary markers: No specific markers or instructions to ignore embedded commands are present. Capability inventory: The skill does not possess any dangerous capabilities such as file-system modification, shell access, or external data transmission beyond its primary purpose. Sanitization: No explicit sanitization or validation of the retrieved documentation is defined. This surface is considered safe given the skill's restricted scope and the intended use case of providing technical documentation.

context7-mcp