The Agent Skills Directory

[SAFE]: The skill is entirely instructional, providing a taxonomy of psychological principles (e.g., Social Proof, Scarcity, Anchoring) and mental models (e.g., First Principles, Pareto Principle) for use in marketing contexts.
[INDIRECT_PROMPT_INJECTION]: The skill encourages the agent to read context from local files such as .agents/product-marketing.md to tailor its recommendations. While this introduces a potential surface for indirect prompt injection if those files contain malicious instructions, it is a standard design pattern for providing project-specific context and does not involve any high-risk capabilities like shell execution or network exfiltration.
[NO_CODE]: There are no scripts, binaries, or automated tool invocations included in the skill, which significantly reduces the attack surface.

marketing-psychology