audit website for SEO, security, performance and 200+ other issues

Audit websites for SEO, performance, security, technical, content, and 15 other issue cateories with 230+ rules using the squirrelscan CLI. Returns LLM-optimized reports with health scores, broken links, meta tag analysis, and actionable recommendations. Use to discover and asses website or webapp issues and health.

This skill is an instruction-only wrapper for the squirrel CLI and appears coherent. Before installing/using: (1) install the squirrel CLI from the official site and verify its binary provenance; (2) be aware audits crawl live sites and can affect site performance — prefer staging for intrusive deep scans; (3) the CLI will create/modify a local squirrel.toml and cache a project DB in your working directory — run it in an appropriate folder and review created files; (4) avoid piping sensitive site data to external LLMs or untrusted endpoints (e.g., piping to a remote model could expose site content or secrets); (5) check the project license and docs linked in the SKILL.md. If you need the agent to avoid reading local files or external model calls, restrict its allowed tools or run audits manually.

Type: OpenClaw Skill Name: squirrelscan Version: 1.0.4 The skill is classified as benign. While it requests broad `Read` and `Edit` file permissions and `Bash(squirrel:*)` execution, these capabilities are plausibly needed for its stated purpose of auditing and fixing website issues. Crucially, the `SKILL.md` instructions for the AI agent repeatedly emphasize user consent and review before making any changes or taking ambiguous actions, mitigating the risk associated with broad permissions. There is no evidence of intentional harmful behavior, data exfiltration, persistence, or obfuscation.