creating-skills

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

• Third-party content exposure detected (high risk: 0.80). The skill's Step 0 instructions explicitly tell the agent to check the Skills Catalog by visiting the public GitHub repository (https://github.com/All-The-Vibes/skills-catalog) or using WebFetch/WebSearch, which requires fetching and interpreting untrusted, user-generated third-party web content as part of the workflow.