growth
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection because it is designed to ingest and audit untrusted data from external websites.
- Ingestion points: The agent analyzes external website source code, meta tags, and JSON-LD structured data during SEO and Generative Engine Optimization (GEO) audits, as outlined in
SKILL.mdandreference/seo-audit.md. - Boundary markers: The skill does not specify boundary markers or include instructions for the agent to disregard potential instructions embedded within the audited web content.
- Capability inventory: The skill is capable of generating implementation code (HTML, JS, TS) and proposing site-wide SEO or tracking configuration changes.
- Sanitization: No explicit sanitization or filtering of external input is described in the provided instructions.
Audit Metadata