The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and configuration files for strategy and evaluation. No executable scripts, binaries, or automated command execution logic were found.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external context from local files such as .agents/product-marketing.md or product-marketing-context.md if they exist. This is a standard ingestion surface for agentic workflows to gather project context.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (referenced in SKILL.md).
Boundary markers: Not explicitly defined for these files, relying on the agent's internal reasoning.
Capability inventory: References external SEO integrations (semrush, ahrefs, GSC) for manual or tool-assisted analysis (SKILL.md).
Sanitization: Not specified for the ingested context files.
[SAFE]: All external references target trusted organizations or well-known technology services, including Google Developers, llmstxt.org, and Brave Search. These references are used for documentation and official guidance purposes.

ai-seo