seo-optimization
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
npx lighthouseto perform performance and SEO audits. Whilenpxcan execute remote packages,lighthouseis a well-known and trusted tool maintained by Google. - [EXTERNAL_DOWNLOADS]: The skill utilizes
curlto fetchrobots.txtandsitemap.xmlfiles from user-specified target domains for technical SEO auditing. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external websites using
WebFetchandWebSearch. * Ingestion points: External website content fetched viaWebFetchandWebSearchtools. * Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions within the fetched web content. * Capability inventory: The skill has access to powerful tools includingBash,Write, andEdit. * Sanitization: There is no explicit sanitization or validation of the content retrieved from external URLs before processing.
Audit Metadata