The Agent Skills Directory

[SAFE]: The skill provides guidelines and templates for copywriting and does not include any executable scripts, network requests, or credential-gathering operations.\n- [DATA_EXFILTRATION]: The skill references local project files ABOUT-ME.md and MY-ICP.md to inform its writing style. These are context files for brand voice and do not contain sensitive system secrets or credentials.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from ABOUT-ME.md and MY-ICP.md (root). No explicit boundary markers or sanitization logic are present in SKILL.md. However, the capability inventory for SKILL.md shows no subprocess calls, exec/eval, file-write, or network operations, which limits the risk of harmful execution from injected content.

copywriting