The Agent Skills Directory

[SAFE]: No security issues were detected. The skill contains instructions and best practices for SEO auditing.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data from websites using tools like web_fetch or browser-based DOM queries. While this creates a theoretical surface for indirect prompt injection, the skill does not have capabilities that allow the agent to execute dangerous shell commands or perform file-system operations based on that content. Evaluation chain: 1. Ingestion: web_fetch, curl, browser tool. 2. Boundary markers: Absent. 3. Capability inventory: No high-risk capabilities (write/exec) detected. 4. Sanitization: Absent.\n- [EXTERNAL_DOWNLOADS]: The skill refers to well-known and trusted external services such as Google Search Console, Google PageSpeed Insights, and the Rich Results Test. These are informational references for the agent to recommend or use for site analysis and do not involve unauthorized background downloads or remote code execution.

seo-audit