hreflang-check
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by processing external data.
- Ingestion points: The process reads raw HTML source code, HTTP headers, and XML sitemaps provided by the user in Step 2.
- Boundary markers: There are no instructions defining boundaries or delimiters to separate ingested content from system instructions.
- Capability inventory: The skill is limited to performing technical SEO audits and generating report outputs; it lacks command execution or network access capabilities.
- Sanitization: The instructions do not specify any validation or sanitization of the external data before it is analyzed by the agent.
Audit Metadata