The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown content. No scripts, binaries, or automated command executions are included in the package.
[DATA_EXFILTRATION]: While the skill involves analyzing website data and Google Search Console information, it utilizes defined tools from a specified MCP server (thatseoagent) and does not contain hardcoded credentials or unauthorized data transmission patterns.
[PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety guidelines or override agent behavior. It identifies a standard surface for indirect prompt injection (ingesting untrusted web content), which is inherent to SEO audit tasks, but contains no evidence of malicious intent or exploitation techniques.

technical-seo