ui-ux-pro-max

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The workflow runs search.py via run_shell_command to gather “comprehensive information” from external domains at runtime; that script likely fetches public web content and feeds the scraped/free-form text into the agent’s LLM context, creating an indirect prompt-injection risk from outsider-authored pages.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)