The Agent Skills Directory

[SAFE]: The skill instructions and templates are focused on legitimate marketing and SEO tasks. No prompt injection, DAN-style overrides, or bypass patterns were detected.
[SAFE]: Access to local context files like .agents/product-marketing.md is a standard practice for providing relevant context to the agent and does not involve exfiltration of sensitive system credentials or files.
[SAFE]: No obfuscation techniques such as Base64 encoding, zero-width characters, or homoglyphs were found in the skill body or metadata.
[SAFE]: The skill does not include any remote code execution, external package installations, or dynamic context injection commands.

competitors