openclaw-agent-feishu-onboarding
v1.0.1Create OpenClaw agents and onboard Feishu routing with explicit multi-step confirmations. Use when the user needs to (1) define a new agent role and workspac...
⭐ 0· 87·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, SKILL.md, command examples, and the included Python validator all consistently target creating agents and applying/validating Feishu routing in a local OpenClaw config (openclaw.json). Nothing requested (no env vars, no external services) is disproportionate to that purpose.
Instruction Scope
SKILL.md explicitly instructs reading and writing the local OpenClaw config and running openclaw CLI commands and the included validator; this is expected for the stated task. Note: the skill will read potentially sensitive local config (openclaw.json) — the README warns of this and requires multi-step confirmations before writes.
Install Mechanism
No install spec; this is an instruction-only skill with a small included Python script. Nothing is downloaded or written by an installer, minimizing install-time risk.
Credentials
The skill requests no environment variables or credentials. The validator reads OPENCLAW_CONFIG_PATH (if set) and the local filesystem to access openclaw.json; this is proportional to validating local routing config but means the skill requires access to potentially sensitive local config files.
Persistence & Privilege
The skill is not always-enabled and agents/openai.yaml sets allow_implicit_invocation: false, so it won't be implicitly invoked. It does instruct making persistent changes to local config only after explicit multi-step confirmations — appropriate for the task.
Assessment
This skill appears to do what it claims: read your local openclaw.json, guide interactive confirmations, run openclaw CLI commands, and use the bundled Python validator. Before running it: (1) run in a trusted environment because it reads/writes local config files that may contain sensitive data; (2) back up your openclaw.json (or snapshot bindings) before any write; (3) review the validator script (scripts/validate_feishu_bindings.py) yourself to confirm there are no network calls — it performs only local JSON checks; (4) ensure the openclaw CLI you’ll invoke is the genuine binary you expect; and (5) keep the four-step confirmation protocol and require an explicit human go/no-go before any write operations.Like a lobster shell, security has layers — review code before you run it.
latestvk979man73fcjqs5ad7ffpn19hh83bm3x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.