blog-seo-check
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by design.
- Ingestion points: The skill ingests untrusted data from local files (via
Read,Grep,Glob) and remote websites (viaWebFetch) to perform SEO analysis. - Boundary markers: There are no explicit markers or instructions to treat the analyzed content as data only, increasing the risk that embedded instructions in blog posts or meta tags could be executed by the agent.
- Capability inventory: The skill utilizes tools including
WebFetch(network access),Read,Grep, andGlob(filesystem access). - Sanitization: No sanitization, filtering, or validation is performed on the content retrieved from external sources or local files before it is processed by the AI.
Audit Metadata