diagnose-seo
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The agent is directed to fetch and analyze
robots.txt, XML sitemaps, and page content from external domains (SKILL.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are provided to protect against malicious content in the fetched data.
- Capability inventory: The skill leverages the agent's network fetching capabilities and mentions the use of MCP tools for site audits.
- Sanitization: No sanitization or validation logic is defined for the external content before processing.
- [NO_CODE]: The skill contains only instructional text and does not provide any executable scripts or binaries.
Audit Metadata