The Agent Skills Directory

[SAFE]: The skill is purely instructional and provides a diagnostic framework for paid ads. It does not include any executable scripts, binary files, or automated commands that could interact with the host system or network.- [PROMPT_INJECTION]: The skill instructs the agent to process untrusted data such as campaign exports, CRM data, and landing pages (SKILL.md). While this creates an indirect prompt injection surface, the skill lacks the necessary capabilities (such as file system writes, network requests, or shell execution) to exploit such an injection. No boundary markers or sanitization methods are specified for the incoming data.

paid-ads