QA Checklist

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

• Third-party content exposure detected (high risk: 0.85). The runtime workflow uses curl -s https://ethskills.com/qa/SKILL.md to fetch and ingest free-form text from an external public web page (outsider-authored content) 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 fetch and instruct the agent to "Read https://ethskills.com/qa/SKILL.md" via "curl -s https://ethskills.com/qa/SKILL.md", so remote content at that URL is loaded at runtime and directly controls agent instructions.