ui-ux-design

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow (Step 2 "Search Relevant Domains") instructs the agent to run .claude/skills/ui-ux-design/scripts/search.py with arbitrary keywords and domain flags to gather and synthesize search results from external/public domains, meaning untrusted third-party web content will be fetched and can influence the agent's decisions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill instructs running system-level installation commands (e.g., "sudo apt update && sudo apt install python3") and expects executing scripts on the host, which directs the agent to perform privileged state-modifying actions.