generative-engine-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it is designed to fetch and process raw HTML and configuration files from user-provided URLs.
- Ingestion points: External content is retrieved using
curlinSKILL.md(Step 1) to audit the visibility and citability of a website. - Boundary markers: The instructions do not specify explicit delimiters or markers to separate the fetched content from the agent's instructions.
- Capability inventory: The skill utilizes
curlfor fetching remote resources. - Sanitization: No specific sanitization or escaping mechanisms are mentioned for the external HTML content.
- [COMMAND_EXECUTION]: The skill instructions utilize
curlto perform network operations. This is a standard functional requirement for auditing website metadata, robots.txt, and server-rendered HTML.
Audit Metadata