The Agent Skills Directory

[SAFE]: The skill consists of instructional markdown files and structured reference data for copywriting. No executable code, shell commands, or automated tools are used or permitted by the configuration.
[SAFE]: There are no network operations, external downloads, or attempts to access sensitive system files or credentials.
[SAFE]: Indirect prompt injection risk is negligible. While the skill instructs the agent to read local configuration files for context, it possesses no capabilities (such as file-writing or network access) that could be exploited by malicious content within those files.

cold-email