brand-content-design

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to WebFetch the public index at https://camoa.github.io/dev-guides/llms.txt and then fetch specific topic pages "when extracting brand elements or analyzing design systems," which means the agent will ingest and act on untrusted third‑party web content (SKILL.md "Online Dev-Guides" section).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to "WebFetch the index" at runtime from https://camoa.github.io/dev-guides/llms.txt and then fetch specific topic pages to drive design-system extraction/analysis, so remote content is retrieved during runtime and used to control prompts/instructions.