seo-optimizer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill provides instructions for the agent to audit external website content, including
robots.txtandsitemap.xml. While this creates an ingestion point for untrusted data, the skill's defined capabilities are limited to analysis and reporting, which poses minimal risk. - Ingestion points: Website HTML,
robots.txt, and XML sitemaps. - Boundary markers: None explicitly defined in the templates.
- Capability inventory: The checklist suggests using
curlfor manual header and file inspection. - Sanitization: Not applicable as the output is a descriptive audit report.
- [Command Execution] (LOW): The
analysis-checklist.mdfile contains a section for command-line tools suggesting the use ofcurlto inspect site headers and robots files. These are standard diagnostic commands with no hazardous flags. - [No Skill Definition] (INFO): The provided files are reference markdown documents. A standard AI skill package typically includes a
SKILL.mdfile for task orchestration which is absent here.
Audit Metadata