cekura-bot-test-writer

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow uses GitHub Actions to automatically read and process pull requests, which contain outsider-authored free text in PR descriptions, comments, and code diffs.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs loading skill material via npm from a third-party organization repo (cekura-ai/cekura-skills), which constitutes an unverified runtime external dependency tier high.