QA Checklist

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

• Third-party content exposure detected (high risk: 0.95). The required workflow uses curl -s https://ethskills.com/qa/SKILL.md to fetch and ingest free-form text from an external public web page into the agent’s LLM context, which is outsider-authored content.

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 explicitly run and instruct the agent to fetch and read remote content at https://ethskills.com/qa/SKILL.md (via "curl -s https://ethskills.com/qa/SKILL.md" and "Tell your agent: 'Read https://ethskills.com/qa/SKILL.md and audit this dApp'"), and also references installing a plugin from https://github.com/austintgriffith/ethskills, so remote content/code is fetched at runtime and can directly control prompts or execute code.