Skill Install Guard｜技能安装守门员

Performs a five-step guarded skill install with checks for existence, local state, risk, execution, and post-install verification.

This package is largely what it says: a local vetter that enumerates files, fetches source metadata, reports red flags, and optionally runs a supplied install command. Before you run it: (1) review scripts/skill-install-guard.py yourself for any surprising behavior (notably it references /home/baiwan/.openclaw/workspace-assistant-shrimp — an unexplained hard-coded path); (2) run in dry-run mode (--dry-run or --stop-before-install) first and inspect the JSON report; (3) never pass unreviewed install commands — the tool will execute the exact command you provide (it disallows shell operators but can still run any binary); (4) run it in an isolated environment if you are concerned about local data exposure; and (5) if you need higher assurance, ask the author why the hard-coded workspace path is present or modify the script to use only explicit, documented local roots.

Type: OpenClaw Skill Name: shrimp-skill-install-guard Version: 0.4.3 The skill bundle provides a security-focused installation workflow that performs static analysis and risk assessment on other skills. The core script, `scripts/skill-install-guard.py`, uses regex-based rules to scan for sensitive data access, credentials, and dangerous code patterns (e.g., searching for `~/.ssh`, `eval`, or OpenClaw-specific files like `SOUL.md`). While the tool is designed for defense and includes security features like shell-injection mitigation in its command execution logic, it possesses high-risk capabilities such as executing arbitrary commands via the `--install-cmd` argument and performing network requests to GitHub and ClawHub APIs. These capabilities are necessary for its stated purpose but meet the threshold for a suspicious classification due to the inherent risk of the provided functionality.