cankun-blog-preview

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local development scripts via bun run previews and bun run build to process images and verify the site. These operations are restricted to the local workspace and intended project lifecycle.
  • [PROMPT_INJECTION]: The agent reads local MDX content to generate visual metaphors. While this involves processing external data, the logic is strictly bound to visual synthesis, and the skill includes a user-in-the-loop requirement ('Ask the user to choose') for ambiguous cases.
  • [SAFE]: No external network dependencies, remote code downloads, or credential exposures were detected. The skill maintains project-specific naming conventions and file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 12:24 PM
Security Audit — agent-trust-hub — cankun-blog-preview