The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any executable code, scripts, or subprocess calls that could be used for malicious purposes.
[SAFE]: It includes a robust safety framework in the 'Risk Gates' section, explicitly identifying high-risk operations like DNS changes, subscriber imports, and live sends, and mandating human approval before proceeding.
[SAFE]: No indicators of prompt injection, data exfiltration, obfuscation, or unauthorized network operations were found in any of the skill files.
[SAFE]: Although the skill processes external data such as reader surveys and replies (creating an indirect prompt injection surface), it lacks the capabilities (like file writing or network requests) that would make such an injection exploitable.

newsletterskill