better-icons

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow uses the MCP/CLI tools to call Iconify’s public API (https://api.iconify.design) to fetch icon SVG/text, which is outsider-authored content that can be ingested into the agent’s LLM context via the tool outputs (e.g., get_icon/get_icons).