The Agent Skills Directory

[SAFE]: The skill does not contain any malicious patterns such as prompt injection, credential exfiltration, or obfuscation. Its primary purpose is to guide an AI agent through a marketing strategy workflow.
[NO_CODE]: The skill is composed of Markdown instructions and evaluation data. It does not ship with any Python, Node.js, or shell scripts, eliminating the risk of direct remote code execution or persistence mechanisms.
[INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting external business data (e.g., traffic reports and conversion lag data). While this constitutes an attack surface for indirect prompt injection, the skill does not request or use tools with high-privilege capabilities (like shell execution or file modification), and the instructions focus on analytical tasks, which minimizes the impact of potentially malicious data content.

retargeting-funnel