The Agent Skills Directory

[SAFE]: The skill operates entirely within its documented purpose of auditing project SEO. Detailed analysis of all provided scripts and instructions confirms they do not contain hidden backdoors, obfuscated code, or unauthorized network operations. Artifacts are stored in a predictable local directory using standard file management practices.- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it is designed to ingest and analyze external project files (HTML, robots.txt, sitemaps, etc.). This is a known risk for any content-processing agent but is classified as low severity here given the skill's specific auditing focus and absence of instructions that would cause the agent to execute untrusted content. (Ingestion points: Local and remote project files; Boundary markers: Absent; Capability inventory: File read/write access and local script execution; Sanitization: Not explicitly implemented in the provided logic).

seo-maker