The Agent Skills Directory

[SAFE]: No malicious patterns, such as prompt injection or data exfiltration, were detected during the analysis of the skill's instructions and reference files.
[SAFE]: The skill does not include any scripts, binaries, or shell commands, posing no risk of unauthorized code execution or system modification.
[SAFE]: The practice of reading local context files like .agents/product-marketing-context.md is a documented and safe method for providing business context to the agent within a local environment.
[SAFE]: External links are limited to well-known documentation sources for web standards, such as schema.org, and do not lead to untrusted or high-risk domains.

site-architecture