Building Blocks

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

• Third-party content exposure detected (high risk: 0.70). The required workflow runs curl -s https://ethskills.com/building-blocks/SKILL.md, which fetches public web content at runtime; if that fetched text is ingested into the agent’s LLM context, it is outsider-authored free text from an external website.

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

• Potentially malicious external URL detected (high risk: 1.00). The catalog's install and setup explicitly fetch and instruct the agent to "Read https://ethskills.com/building-blocks/SKILL.md" at runtime (via "curl -s https://ethskills.com/building-blocks/SKILL.md"), so external content would directly control agent prompts/instructions and is a required dependency.