Frontend UX

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses curl -s https://ethskills.com/frontend-ux/SKILL.md to fetch and ingest readable text from a public web page at runtime, which is outsider-authored free text (public web content) fed into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's setup and install steps explicitly run curl and tell the agent to "Read https://ethskills.com/frontend-ux/SKILL.md" at runtime (and also reference a GitHub repo https://github.com/austintgriffith/ethskills for plugin install), so externally fetched content will directly control agent prompts/instructions.