The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl and jq to interact with the Mixpanel Query API. All shell commands are localized to the skill's specific analytics functionality and utilize secure environment variable interpolation for authentication parameters.
[EXTERNAL_DOWNLOADS]: Network operations are restricted to verified domains (mixpanel.com and data.mixpanel.com) over HTTPS. This is the intended behavior for fetching analytics data and no unauthorized external connections were detected.
[CREDENTIALS_UNSAFE]: The skill implements safe credential management by explicitly requiring the use of environment variables (MP_SERVICE_ACCOUNT, MP_SERVICE_SECRET, MP_PROJECT_ID). It provides clear guidance in the setup.md file to avoid hardcoding or sharing secrets in the conversation.
[PROMPT_INJECTION]: The skill fetches data from external Mixpanel API endpoints. While this represents a surface for indirect prompt injection, the implementation focuses on structured data retrieval (JSON) and does not contain instructions that would enable the override of agent behavior or safety filters.

Mixpanel