Tools

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses curl -s https://ethskills.com/tools/SKILL.md to fetch readable text from a public web page (outsider-authored content) that the agent may ingest into its LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The catalog explicitly instructs the agent to fetch and read https://ethskills.com/tools/SKILL.md (install.command: curl -s https://ethskills.com/tools/SKILL.md and "Tell your agent: 'Read https://ethskills.com/tools/SKILL.md'"), meaning externally-hosted content is fetched at runtime and can directly control agent instructions.