Contract Addresses

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow runs curl -s https://ethskills.com/addresses/SKILL.md, which fetches outsider-authored free text from a public web page and can be ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's setup and install.command explicitly instruct fetching and reading https://ethskills.com/addresses/SKILL.md at runtime ("curl -s https://ethskills.com/addresses/SKILL.md" and "Read ... before using addresses"), so external content from that URL would directly control agent instructions/behavior and is a required dependency.