install-xzy-skills

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs running "npx skills add sanxzy/Skills --all", which fetches and installs a public GitHub repository (sanxzy/Skills) into the project and requires parsing the CLI output and symlinking those external skills—exposing the agent to untrusted third-party code and output that can influence subsequent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs "npx skills add sanxzy/Skills --all", which fetches and installs the external GitHub repository (https://github.com/sanxzy/Skills) at runtime and thus pulls in remote skill files that can directly control agent prompts or execute code.