review-generated-automated-test

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow ingests the repository diff via git --no-pager diff ... origin/master...HEAD, which includes outsider-authored free text from other contributors’ commits (e.g., PR/branch changes) into the agent’s LLM context for review.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)