The Agent Skills Directory

[SAFE]: The skill provides standardized tools to resolve library identifiers and query documentation from the Context7 API. The instructions explicitly advise against including sensitive data in queries, following security best practices.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source (documentation snippets from Context7), which introduces a theoretical surface for indirect prompt injection if the source data contains malicious instructions. However, the skill does not possess high-privilege capabilities that would allow such an injection to be exploited.
Ingestion points: Documentation and code examples returned by the query-docs tool.
Boundary markers: None defined in the skill instructions.
Capability inventory: The skill provides read-only documentation access and does not include tools for file system modification, network exfiltration of local data, or arbitrary command execution.
Sanitization: No explicit sanitization or validation of the retrieved documentation content is described in the skill metadata or workflow.

context7