The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or configuration.
[DATA_EXFILTRATION]: The skill facilitates data transmission to the Context7 MCP service for documentation retrieval. This is the primary intended functionality. The instructions specifically mandate that the agent redact API keys, passwords, and tokens from any data sent externally, representing a security best practice.
[PROMPT_INJECTION]: The skill involves an indirect prompt injection surface through the ingestion of external documentation content via the query-docs tool.
Ingestion points: External documentation retrieved via the query-docs tool output.
Boundary markers: None explicitly defined in the instructions.
Capability inventory: The skill does not define or use high-risk tools (e.g., shell execution, file system modifications) that could be exploited via injected content.
Sanitization: No content sanitization is performed, but the risk is assessed as minimal due to the limited capability scope of the skill.

documentation-lookup