brand-agency

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Node.js script scripts/render-templates.js that uses the Playwright library to launch a Chromium browser instance. The script also performs file system operations, including creating directories (fs.mkdirSync) and writing image files (page.screenshot) to paths specified via command-line arguments.
  • [EXTERNAL_DOWNLOADS]: The HTML templates located in assets/templates/ utilize CSS @import rules to fetch font files from fonts.googleapis.com (Google Fonts). This is a standard practice for web-based typography and involves communication with a well-known, trusted service.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a workflow where the agent is encouraged to use HTML templates to generate visual artifacts. This creates a potential surface where untrusted data (such as user-provided text for a post) could be inserted into the HTML and subsequently rendered by a headless browser. While this presents an injection surface, the risk is mitigated by the isolated nature of the rendering environment and the intended use-case of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 04:42 AM