The Agent Skills Directory

[SAFE]: The skill instructions define a purely informational and strategic framework for content planning. It does not use any computational tools, perform network operations, or access sensitive system files. The instructions to read project-specific marketing context files (e.g., .agents/product-marketing.md) are standard for context-aware agents and do not involve exposure of system-level secrets.
[NO_CODE]: The skill consists entirely of Markdown documentation and JSON configuration. There are no scripts (Python, JavaScript, etc.) or binary files included, which significantly reduces the risk of malicious code execution.
[PROMPT_INJECTION]: The skill is designed to process external, untrusted data such as keyword exports, call transcripts, and survey responses. While this represents an ingestion surface for indirect prompt injection, the skill's capabilities are limited to generating text-based recommendations and tables within the conversation. It lacks the ability to execute code or perform network requests that could be used for data exfiltration.

content-strategy