The Agent Skills Directory

[SAFE]: No security risks identified. The skill content is restricted to educational guidelines, platform-specific constraints, and content templates.
[DATA_EXPOSURE]: The skill suggests reading .agents/product-marketing-context.md to personalize content. This is a localized context-gathering mechanism and does not involve accessing sensitive system files, environment variables, or user credentials.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion point for untrusted data via the product marketing context file. However, there are no capabilities such as network operations, file writing, or command execution that could be exploited through this vector. No specific boundary markers are present, but the risk remains negligible given the lack of executable capabilities.

social-content