kuikly-compose-ui-framework

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required runtime workflow clones/pulls the public GitHub repo KuiklyUI (insider text: public web content) into references/KuiklyUI, and the skill then instructs the agent to read markdown/source files from that directory (read_file/resource lookup), which will feed outsider-authored free text into the LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly clones/pulls the repository https://github.com/Tencent-TDS/KuiklyUI (and https://github.com/Tencent-TDS/KuiklyUI.git) at runtime and mandates using that repository's docs/source to drive responses, so the fetched external content directly controls prompts and is a required dependency.