감사 이력
nanobanana - 2 감사
감사 버전 2
최신 중간 위험Jun 28, 2026, 01:39 PM
Static analysis reported many severe patterns, but manual review shows no confirmed malicious intent and no prompt injection attempts. The main real risks are expected for this skill type: environment API key access, external Gemini API calls, local image file reads for edit and restore, automatic dependency bootstrap, and a documented pipe-to-shell uv installer command.
중간 위험 문제 (3)
낮은 위험 문제 (3)
위험 요인
⚡ 스크립트 포함 (2)
🌐 네트워크 접근 (4)
📁 파일 시스템 접근 (4)
🔑 환경 변수 (4)
⚙️ 외부 명령어 (3)
감지된 패턴
감사 버전 1
안전May 4, 2026, 09:53 AM
Static analysis detected 216 potential issues but manual evaluation confirms all are false positives. The skill is a legitimate image generation tool using Google's Gemini API. Network calls go exclusively to Google's official API endpoints. Environment variable access is standard API key configuration. Subprocess usage is limited to safe desktop integration (image preview). Base64 decoding handles image data from API responses. No credential exfiltration, data leakage, or malicious behavior detected.