gate-seo
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes '前端代码' (Frontend code) as its primary input to perform SEO fixes and metadata generation.
- Ingestion points: The skill ingests code via the 'input' field and instructions to search and modify page source files (
page.tsx). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands in the input code are present.
- Capability inventory: The skill possesses the capability to modify source files, export metadata, and update configuration files such as sitemaps and robots.txt.
- Sanitization: There is no evidence of sanitization or validation of the input code before it is processed by the agent's logic.
Audit Metadata