The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions define a clear persona as an SEO expert and do not contain any patterns intended to bypass safety filters or override system instructions.
[DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were detected. The skill utilizes local context files like MEMORY.md and USER.md to personalize the audit, which is a standard and safe platform feature.
[EXTERNAL_DOWNLOADS]: The skill references the use of web_fetch and curl for the purpose of retrieving website metadata and performing page speed checks. These operations are standard for the skill's purpose and are targeted at user-specified domains.
[REMOTE_CODE_EXECUTION]: There is no evidence of downloading and executing scripts from remote sources. Recommendations for using browser tools to detect schema markup involve standard DOM queries and do not involve executing untrusted code on the host system.
[COMMAND_EXECUTION]: The skill uses commands like curl for technical diagnostics (checking robots.txt and sitemaps), which is an appropriate and safe use of the tool within the context of an SEO audit.
[SAFE]: Overall, the skill follows best practices for SEO auditing and provides detailed guidance on avoiding AI-generated writing tells without any malicious intent.

seo-audit