The Agent Skills Directory

[SAFE]: The skill provides structured frameworks and guidelines for generating social media content. It references local context files and knowledge directories which are standard for personalizing agent responses within supported environments.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from a knowledge base and repurpose user-provided content. While this involves processing untrusted data, the skill only performs text generation and does not utilize any high-privilege tools or execute code, neutralizing the risk of exploitation through data poisoning.

twitter-thread