The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data, specifically Playwright configurations and component inventories, to define and execute testing logic. This creates a surface for indirect prompt injection as the skill lacks explicit boundary markers or sanitization logic for these external inputs. The risk is partially mitigated by instructions to use isolated local fixtures and to verify evidence before drawing conclusions.- [COMMAND_EXECUTION]: The workflow relies on executing shell commands for Playwright tests and vendor-specific utilities such as t3u. While these are intended for use within a local development environment for testing purposes, they involve the execution of commands derived from project-controlled configuration files.- [EXTERNAL_DOWNLOADS]: The skill provides links to official Playwright documentation and vendor-controlled GitHub repositories. These references target well-known services or the author's own resources for technical guidance and do not represent unauthorized or malicious remote code execution vectors.

typo3-playwright