Back to skill
Skillv0.3.2
VirusTotal security
OpenClaw Smartness Eval · External malware reputation and Code Insight signals for this exact artifact hash.
Scanner verdict
BenignApr 30, 2026, 6:31 AM
- Hash
- 5bcdb290833abf2f8694878ae0192496a61befa1b6068ad69f2016ea75a03389
- Source
- palm
- Verdict
- benign
- Code Insight
- Type: OpenClaw Skill Name: openclaw-smartness-eval Version: 0.3.2 The openclaw-smartness-eval bundle is a comprehensive framework designed to measure AI agent performance across 14 dimensions. While the core logic in `scripts/eval.py` utilizes `subprocess` to execute test commands, it implements a robust security gate (`validate_command`) that enforces a whitelist of allowed path prefixes, restricts the interpreter to `python3`, and explicitly blocks inline code execution (`-c`, `exec`), absolute paths, and path traversal. Data collection is limited to local workspace state files and logs, and the optional network access for LLM-based scoring is documented and requires user-provided API keys. The bundle demonstrates high transparency and security-conscious design, including anti-gaming probes and integrity checks.
- External report
- View on VirusTotal