Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Openclaw Agent Builder
v0.1.0Use when creating OpenClaw agents, configuring workspaces, multi-agent routing, session isolation, or channel bindings.
⭐ 1· 373·2 current·2 all-time
bySiHan Song@a12591771
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The skill's name/description match the SKILL.md content: it documents creating agents, workspaces, bindings, and session isolation, and shows expected config files (~/.openclaw, AGENTS.md, SOUL.md, auth.json). The examples (openclaw CLI, config JSON) are appropriate for an agent-builder guide.
Instruction Scope
SKILL.md directs the agent/operator to read and write local configuration and session files (e.g., ~/.openclaw/openclaw.json, ~/.openclaw/agents/<id>/auth.json, sessions JSONL, TOOLS.md). This is consistent with building/configuring agents but means the skill will operate on potentially sensitive local files and credential locations; users should be aware and inspect those files before granting access.
Install Mechanism
Instruction-only skill with no install spec or code files. That minimizes disk-write/remote-download risk. It does presume an existing 'openclaw' CLI, but provides no installer (which is reasonable for a docs-style guide).
Credentials
The registry metadata declares no required env vars or credentials, yet the guide references auth.json and '认证凭据位置' and mentions database connection strings in TOOLS.md. Requesting/reading local credential files is proportionate for an agent-builder, but because the skill can direct access to those credential locations, users should verify where secrets are stored and restrict access accordingly.
Persistence & Privilege
No elevated persistence requested (always: false). The skill does not claim it will modify other skills or system-wide agent settings. Autonomous model invocation is allowed (platform default) but not accompanied by broad privileges in metadata.
Assessment
This SKILL.md appears to be a legitimate guide for creating OpenClaw agents, but it instructs reading and writing files under ~/.openclaw (including auth.json and session histories) and references places where credentials might be stored. Before installing or enabling this skill: 1) Confirm you trust the OpenClaw CLI binary and its source on your system (the guide expects 'openclaw' to be present). 2) Inspect ~/.openclaw and the referenced files (auth.json, AGENTS.md, TOOLS.md, etc.) to ensure no sensitive secrets would be exposed to an agent you run. 3) Backup any config before applying changes. 4) If you run agents that will execute code or have 'exec' permissions, use sandboxing and least privilege (deny write/exec where unnecessary). 5) If you need higher assurance, test in an isolated environment or VM first. If you want, I can highlight exact lines in SKILL.md that reference credential locations and commands to watch for.Like a lobster shell, security has layers — review code before you run it.
latestvk97arwgnqz12x59ty4xxcq9qeh8204s9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🦞 Clawdis