enhance-web-seo
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection by ingesting untrusted data from the public web.
- Ingestion points: Publicly accessible routes are audited via Playwright, capturing titles, descriptions, headings, and JSON-LD data (SKILL.md Phase 1).
- Boundary markers: The instructions do not employ delimiters or ignore-instructions for the data retrieved from external web pages.
- Capability inventory: The skill is authorized to modify application source files (Next.js, Remix, SvelteKit) to implement SEO fixes (SKILL.md Phase 4).
- Sanitization: The skill lacks sanitization logic to filter out potential prompt injection payloads embedded in meta tags or structured data before processing them.
Audit Metadata