nextjs-seo
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external data, which inherently creates an indirect prompt injection surface.
- Ingestion points: The agent is directed to read production HTML, inspect URL responses, and process Search Console data (see
SKILL.mdandreferences/checklist.md). - Capability inventory: The agent uses this information to perform diagnostic audits and provide implementation advice. No automated code execution on external data is described.
- Sanitization: The skill proactively recommends security measures in
references/json-ld.md, specifically advising the use of safe serialization techniques (e.g., escaping<characters) to prevent cross-site scripting (XSS) when generating structured data. - [EXTERNAL_DOWNLOADS]: The skill includes multiple references to official technical documentation and crawler policy pages from well-known technology providers.
- Documentation links include official domains for Google, OpenAI, Anthropic, and Perplexity for the purpose of verifying search engine and AI crawler behavior.
Audit Metadata