The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill uses node -e to execute inline JavaScript for discovering the Puppeteer version and the browser's executable path. This execution is static and limited to environment discovery.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads and searches through local JavaScript and TypeScript files. This presents an indirect prompt injection surface as it ingests potentially untrusted data into the agent's context. However, the skill includes explicit instructions against executing or modifying scripts without user approval, which serves as a safety boundary.

managing-puppeteer