codex-first-customer-finder-skill

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

• Third-party content exposure detected (low risk: 0.10). The skill searches and ingests public discussions, forums, and social posts to find potential customer leads, which constitutes low-risk outsider text retrieval.

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

• Potentially malicious external URL detected (medium risk: 0.30). The installation instructions reference an unofficial third-party GitHub repository and an npm package without an official registry URL to fetch skill code during runtime or setup, making it an unverifiable third-party dependency.