Back to skill
Skillv1.0.7
ClawScan security
Nex.ai · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 21, 2026, 8:46 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's code, runtime instructions, and requested credential (NEX_API_KEY) are consistent with its stated purpose of calling the Nex developer API; nothing requests unrelated secrets or installs arbitrary third‑party code.
- Guidance
- This skill appears coherent and limited to calling Nex's developer API. Before installing: (1) create and use a least-privilege Nex API key (grant only the scopes you need; prefer read-only for queries), (2) keep the key in your OpenClaw skill config (do not paste into chat), (3) review and trust the Nex service at https://app.nex.ai before sharing org data, and (4) be aware the agent may call Nex autonomously—limit scopes or disable autonomous invocation if you want manual control. If you need higher assurance, inspect the included scripts yourself and consider rotating the key after testing.
Review Dimensions
- Purpose & Capability
- okName/description match the actual behavior: the skill is an API client for Nex and only requires NEX_API_KEY plus standard CLI tools (curl, jq, bash). These requirements are proportionate to querying and managing records via Nex.
- Instruction Scope
- okSKILL.md confines runtime actions to using the included wrapper script and Nex endpoints. It documents safe patterns (reading API key from env, piping JSON via stdin, validating JSON, restricting API paths) and does not instruct reading unrelated files or other environment variables.
- Install Mechanism
- okNo install spec or external downloads; the skill is instruction-only and ships a small wrapper script. Nothing is fetched from arbitrary URLs or written outside the skill workspace.
- Credentials
- okOnly the primary credential NEX_API_KEY is required. The script uses that key only in Authorization headers to the hardcoded Nex base URL. No unrelated credentials or system config paths are requested.
- Persistence & Privilege
- okThe skill is not always-enabled and does not request elevated platform privileges or modify other skills. It can be invoked autonomously (default), which is expected for an API integration; users should be mindful of agent autonomy when granting access.