blog-rewrite

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process external blog content (MDX, markdown, HTML) which may contain embedded instructions (indirect prompt injection surface). However, this is inherent to the skill's purpose as a rewriter and does not include any instructions that attempt to bypass safety filters or extract system data.
  • [COMMAND_EXECUTION]: The skill instructs the agent to search for keyword cannibalization across the blog directory using file scanning techniques. In Phase 1 Step 5, it mentions using search commands to identify overlapping keywords in headings and meta descriptions.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to source statistics and images for content enrichment. It targets well-known and reputable services such as Pixabay and Unsplash for media sourcing, and standard web searches for verified data points.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 05:48 AM