The Agent Skills Directory

[SAFE]: The skill instructions and reference materials (research-methods.md, tier-structure.md) are strictly educational and advisory. No command execution, network requests, or sensitive file system operations are present.
[SAFE]: The skill suggests reading project-specific context files like .agents/product-marketing-context.md. While this establishes a data ingestion surface, the skill does not request or use any high-risk tools (such as shell access, arbitrary file writing, or network utilities) that could be exploited via indirect prompt injection. Boundary markers and sanitization are absent, but the lack of dangerous capabilities renders the risk negligible.

pricing-strategy