Back to skill
Skillv0.1.0

ClawScan security

Openclaw Skill Minimax Tracker · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignFeb 27, 2026, 9:45 AM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's code, instructions, and requirements are internally consistent with a local MiniMax usage tracker; it stores data in the user's home directory and does not request credentials or network access.
Guidance
This skill appears coherent and low-risk: it only records prompt counts in a JSON file and prints progress bars. Before installing, review/verify the GitHub source (SKILL.md points to a repo) if you don't already trust it. Note that the script writes to ~/.openclaw/workspace/minimax_usage_data.json (check file ownership/permissions). The reset-time logic uses the system local time (the code assumes an UTC+8 reset window but uses naive datetime.now(), which may produce incorrect reset calculations on systems in other timezones) — if correct reset timing is important, review or test that behavior. If you want stronger isolation, run the script in a restricted environment (container or limited-permission user). There are no network calls or credential requests in the packaged code.

Review Dimensions

Purpose & Capability
okThe name/description (MiniMax usage tracker) matches the included Python script and SKILL.md. Required capabilities (none) are proportional to the stated purpose — the skill only reads/writes a local JSON file and prints progress bars.
Instruction Scope
okSKILL.md instructs the agent to invoke the provided script (via subprocess) and to optionally install/copy the skill into the workspace; it does not direct reading of unrelated system files, collection of secrets, or network exfiltration. Integration examples run the local script, which is expected behavior for this skill.
Install Mechanism
okNo install spec is present (instruction-only with an included script). Nothing is downloaded or executed from external URLs; the README suggests cloning a GitHub repo but the packaged files include the script. This is low-risk from an install perspective.
Credentials
okThe skill declares no environment variables, no credentials, and no config paths beyond writing to a user-scoped JSON file (~/.openclaw/workspace/minimax_usage_data.json). That storage need is proportional to a usage-tracking utility.
Persistence & Privilege
okThe skill is not force-included (always:false) and does not request persistent elevated privileges or modify other skills. It only writes its own JSON file in the user's home workspace.