The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown focused on technical SEO, site architecture, and performance auditing. It does not include any scripts, commands, or requests for sensitive information.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit and diagnose external website data, which creates a potential surface for indirect prompt injection. 1. Ingestion points: The agent is instructed to read and analyze technical health, robots directives, site architecture, and content from third-party sites (SKILL.md). 2. Boundary markers: No delimiters or isolation instructions are provided to separate analyzed data from agent instructions. 3. Capability inventory: No tools or dangerous capabilities (such as file-system writes or network requests) are defined or utilized by this skill. 4. Sanitization: No sanitization methods are mentioned. The absence of high-privilege tools makes this a low-risk informational surface.

seo-strategy