The Agent Skills Directory

[SAFE]: The skill consists exclusively of instructional Markdown files and a JSON evaluation file. It does not include any executable scripts (Python, Node.js, Shell), eliminating the possibility of direct code execution.
[SAFE]: No network-related commands (e.g., curl, wget, fetch) or remote data requests are present in the skill body or references.
[SAFE]: There are no attempts to access sensitive system paths, environment variables, or hardcoded credentials. The skill only references standard local context files (e.g., product-marketing.md) for its intended purpose.
[SAFE]: The instructions do not contain prompt injection patterns designed to bypass safety filters, escalate privileges, or modify the underlying agent behavior in a malicious way.
[SAFE]: No obfuscation techniques, such as Base64 encoding of commands, zero-width characters, or homoglyph attacks, were detected in any of the provided files.

cold-email