The Agent Skills Directory

[SAFE]: The skill consists solely of markdown instructions for an expert persona and JSON evaluation data. No executable scripts, binary files, or installation commands were detected.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the skill text or metadata.
[SAFE]: The instruction to read a local context file (.agents/product-marketing-context.md) is a standard practice for agent personalization and does not involve processing untrusted external data or executing remote code.
[SAFE]: All references to external resources are limited to mentions of other related skills, which are handled as plain-text labels.

form-cro