blink-seo-articles

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for installing the 'sharp' image processing library and executing a local script (scripts/generate-og-images.mjs) to generate branded hero images. These operations are standard for the developer-oriented nature of the skill and do not involve untrusted input or risky execution patterns.
  • [EXTERNAL_DOWNLOADS]: The skill uses web_search, google_serp, and fetch_url to perform keyword research and competitor analysis. This is a primary function of an SEO skill. The analyzed URLs are treated as data for content generation and are not executed.
  • [DATA_EXFILTRATION]: No sensitive local data is accessed or transmitted. The skill interacts exclusively with the Blink CMS MCP tools (cms_write_file, cms_publish, cms_read_file) and public web search APIs to perform its tasks.
  • [PROMPT_INJECTION]: The instructions focus on structured content authoring and SEO optimization. There are no attempts to override agent safety guidelines or bypass platform restrictions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 04:52 PM