skills/smixs/seo-blog/blog-seo-check/Gen Agent Trust Hub

blog-seo-check

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external URLs and local files to perform SEO analysis, which presents a surface for indirect prompt injection.
  • Ingestion points: Content is retrieved from external websites via WebFetch (Step 1, Step 6) and from local files using the Read tool.
  • Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded commands when processing retrieved content.
  • Capability inventory: The skill is restricted to read-only tools including Read, Grep, Glob, and WebFetch, with no access to dangerous capabilities like shell execution, network exfiltration, or file system modification.
  • Sanitization: There is no mention of sanitizing or filtering the content retrieved from external sources before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:56 PM
Security Audit — agent-trust-hub — blog-seo-check