The Agent Skills Directory

[NO_CODE]: The analyzed skill consists entirely of Markdown-formatted instructions. It does not include any executable code, scripts, binary files, or configuration files that could be used to perform malicious operations.
[SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found. The instructions are focused solely on email copywriting frameworks and best practices.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote code downloads or execution. There are no calls to package managers (pip, npm) or shell-based downloaders (curl, wget).
[DATA_EXFILTRATION]: No network access or sensitive file system operations are requested or performed. The skill does not interact with credentials, environment variables, or private user data.
[INDIRECT_PROMPT_INJECTION]: While the skill instructs the agent to process external context about email recipients, the skill lacks any capabilities (such as file writing, shell access, or network requests) that could be exploited via malicious data injection.

cold-email