apoco-backend-review

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

• Third-party content exposure detected (high risk: 1.00). The skill's required Step 1 instructs the agent to fetch and read the public GitHub README at https://github.com/ApocoHQ/backend-code-challenge (an open, third-party repo) as the "source of truth" for evaluating submissions, so untrusted external content is ingested and can directly influence scoring and next actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs at runtime to fetch and use the README from https://github.com/ApocoHQ/backend-code-challenge as the "source of truth" for evaluation, so external content from that URL directly controls agent instructions and is a required dependency.