awesome-design-skills-registry

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

• Third-party content exposure detected (low risk: 0.10). The workflow pulls curated community design skills (SKILL.md/DESIGN.md files) from a public registry via the TypeUI CLI, which represents low risk as the agent actively fetches specific community content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs downloading and running the unofficial TypeUI CLI tool from typeui.sh and fetching design skills from an external API during runtime execution.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill prompt suggests using sudo to bypass permission issues when executing an npx command, which could compromise the machine's state.