OpenClaw Smartness Eval

OpenClaw 智能度综合评伌技能。围绕 14 个维度（含规划能力、幻觉控制）输出综合评分、证据、风险与趋势。对齐 CLEAR/T-Eval/Anthropic 行业标准。

This skill is broadly coherent with its stated purpose (a workspace-centered evaluation tool), but before installing: 1) Review eval.py (especially validate_command(), subprocess.run usage, and any code paths that could enable network or write outside its stated output dir). 2) Confirm you trust the other workspace scripts it will invoke (many test commands call scripts that are not bundled). Those external scripts could read secrets or make network calls. 3) Treat the .reasoning/reasoning-store.sqlite and state logs as sensitive — if you don't want those inspected, do not install or run the skill. 4) If you enable --llm-judge, confirm exactly what summary fields are sent and test in an isolated environment first. 5) As a safe practice, run python3 scripts/check.py and then run eval.py in a sandboxed workspace (or with --no-probes / dry-run options) to observe behavior before granting it unfettered access or allowing autonomous invocations.

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.