code-reviewer

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the skill reads and ingests repository file contents and git diffs (outsider-authored code/PR text) into LLM context via the report generator’s JSON/text output: review_report_generator.py → pr_analyzer.py (git diff output) and code_quality_checker.py (read_file_content()), then generate_report() embeds those findings/messages into the final report.