The Agent Skills Directory

[SAFE]: The skill instructions (SKILL.md) follow best practices for information architecture planning and do not contain any prompt injection attempts or attempts to bypass safety filters.
[SAFE]: Data access is limited to reading project-specific context files (e.g., .agents/product-marketing.md), which is a standard method for maintaining context within the agent's environment and does not involve sensitive system files or credentials.
[SAFE]: No network operations, external downloads, or remote code execution patterns were detected across any of the files.
[SAFE]: No obfuscation techniques, such as Base64 encoding of commands or hidden Unicode characters, were found in the instructions or reference templates.
[SAFE]: The skill does not implement any persistence mechanisms or privilege escalation techniques.

site-architecture