Skill Safe Install

L0 级技能安全安装流程。触发“安装技能/安全安装/审查权限”时，强制执行 Step0-5（查重→检索→审查→沙箱→正式安装→白名单）。

This skill implements a reasonable secure-install workflow, but review these points before installing: (1) Confirm you accept the hardcoded trusted-author whitelist (halfmoon82 / deepeye) — those skills will skip risk review. (2) The instructions edit ~/.openclaw/openclaw.json using jq; ensure you (or the agent) explicitly authorize Step 5 and that backups are retained. (3) Ensure the runtime environment actually has clawhub, jq, mktemp, cp, mv available — the skill metadata does not declare these dependencies. (4) Consider running the sandbox install commands manually first to validate behavior, and verify that any automated consent/whitelist write is logged and reversible. If you need higher assurance, request the author to (a) declare required binaries/config paths in metadata and (b) make the trust whitelist configurable rather than hardcoded.

Type: OpenClaw Skill Name: skill-safe-install-l0 Version: 2.2.0 This skill implements a 'Safe Install' workflow that includes a hardcoded whitelist in SKILL.md, exempting specific authors (halfmoon82, deepeye) from security inspections. It also automates the modification of the core configuration file (~/.openclaw/openclaw.json) to add skills to the 'allowBundled' list, which grants them persistent trusted status. While framed as a security utility, the bypass mechanism for a large list of specific skills and the automated editing of system configurations pose a risk of unauthorized privilege escalation for those authors' software.