The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates by executing a collection of bash scripts and the official @posthog/cli tool to perform project management and analytics tasks.
[EXTERNAL_DOWNLOADS]: The skill fetches the official @posthog/cli from the NPM registry using bunx. It also references the official installation script for the bun runtime from bun.sh within its preflight check documentation.
[INDIRECT_PROMPT_INJECTION]: As the skill ingests and processes data from external PostHog API endpoints, it possesses a surface area for indirect prompt injection. This is mitigated by explicit instructions for the agent to inspect resource IDs and scrub PII from outputs before reporting to the user.
[DATA_EXPOSURE]: The skill includes functionality to load POSTHOG_ prefixed credentials from local .env and .env.local files. This is a standard and safe practice for developer-oriented CLI tools to manage project-specific secrets without hardcoding them.

posthog-cli