The Agent Skills Directory

[SAFE]: The skill implements secure credential management by instructing the agent to use environment variables (GRAPHISTRY_PERSONAL_KEY) rather than hardcoding sensitive information like personal keys or JWTs.
[SAFE]: The external resources referenced, including the Graphistry Hub documentation and the PyGraphistry GitHub repository, belong to the verified vendor (Graphistry), representing legitimate service components.
[INDIRECT_PROMPT_INJECTION]: The skill contains an inherent attack surface by processing data from graph sessions that could contain untrusted content. However, this is mitigated by specific instructions to validate all user-provided strings against tool-observed values and the graph schema before use, preventing the agent from acting on unverified instructions found within the data.
[COMMAND_EXECUTION]: The documentation includes curl examples for connecting to the server. These are provided as educational implementation examples for developers and do not constitute a security risk within the skill's operational context.

graphistry-mcp