The Agent Skills Directory

External Downloads (LOW): The README.md file includes a link to an external documentation site (afrexai-cto.github.io) which is not within the defined list of trusted organizations. While currently a static link, external references to untrusted domains are tracked as potential vectors for social engineering or resource substitution.\n- Indirect Prompt Injection (INFO): The skill is designed to process untrusted text input (prospect objections) to provide coaching. It lacks explicit boundary markers or delimiters for this input, creating a surface for indirect prompt injection. However, the risk is negligible (INFO) because the skill possesses no side-effect capabilities such as network access, file system operations, or command execution tools.\n- No Code (SAFE): The skill consists entirely of instructional markdown and metadata. There are no associated Python, Node.js, or Shell scripts, which eliminates the primary attack surface for remote code execution, persistence, and privilege escalation.

Objection Handler