seo-technical
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data via the
WebFetchtool to perform technical audits. This creates a surface where a malicious website could host instructions designed to subvert the agent's task. - Ingestion points: Technical SEO audit of user-provided URLs via
WebFetchinSKILL.md. - Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore any embedded directives in the fetched HTML.
- Capability inventory: Access to
Bash,WebFetch,Read,Grep, andGlobtools. - Sanitization: No evidence of content sanitization or validation of the fetched HTML prior to analysis.
Audit Metadata