The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions and reference data. It does not include any executable code, scripts, or binary files, which eliminates the possibility of direct malware execution or persistence.- [SAFE]: The skill instructs the agent to gather context from local files (e.g., '.agents/product-marketing.md'). This is a standard operational pattern for retrieving internal context and does not involve unauthorized data access or exfiltration.- [SAFE]: No prompt injection or override patterns were detected. The instructions focus on establishing a specific persona and quality standards for email copywriting without attempting to bypass safety filters.

cold-email