awesome-design-skills

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow is installing/pulling a “style skill” from a public community registry (outsider-authored skill package content), where the agent reads the fetched skill’s SKILL.md/DESIGN.md as LLM-readable instructions—i.e., free text authored by others is ingested into the agent context.