Frontend Playbook

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

• Third-party content exposure detected (high risk: 0.95). The required workflow’s runtime step curl -s https://ethskills.com/frontend-playbook/SKILL.md fetches outsider-authored free text from a public web page, which the agent then reads into its 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 explicitly fetch and require remote content at runtime (curl -s https://ethskills.com/frontend-playbook/SKILL.md) and also directs installing a GitHub plugin (https://github.com/austintgriffith/ethskills), meaning external content is retrieved during runtime and can directly control agent instructions or execute code.