The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or unauthorized data access were identified. The skill consists of high-quality instructional content.
[INDIRECT_PROMPT_INJECTION]: The skill instructions include a step to read project-specific context files (e.g., .agents/product-marketing.md). While this identifies a point of entry for external data, the skill itself does not utilize any exploitable tools, network operations, or file-writing capabilities that would pose a security risk. This is a standard context-sharing pattern for the platform.
[EXTERNAL_DOWNLOADS]: No remote code downloads or external package installations are performed. The skill references legitimate marketing tools (e.g., SparkToro, Navattic) only as examples of external services for the user to consider using manually.

launch