Skillv3.0.1

ClawScan security

Tesla Commander · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 24, 2026, 1:49 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is a local reference/cheatsheet implemented as a harmless shell script that only prints documentation; its requirements and instructions match its stated purpose.
Guidance: This skill appears to be a simple, local reference implemented as a shell script that prints documentation—there are no network calls or credential requests. If you plan to install or run it, you can proceed with low risk, but standard precautions apply: review the script yourself (or run it in a sandbox) before allowing any automated agent to execute it, confirm you trust the upstream repository, and be aware that future updates could change behavior. The script has minor non-security bugs (literal $VERSION in help, odd shift usage) but nothing that indicates malicious intent.

Purpose & Capability: okName/description advertise a local reference tool. The skill includes only a SKILL.md and a shell script that print documentation; it requests no credentials, binaries, or config paths. The requested footprint is proportionate to a reference CLI.
Instruction Scope: okSKILL.md states that commands output plain-text via heredoc with no external API calls. The shipped script implements only heredoc outputs and basic CLI dispatch; it does not access files, network, or environment variables. Minor implementation quirk: the help heredoc is single-quoted so the $VERSION token is shown literally rather than expanded, and the script does an extra 'shift' suppressed with redirection—these are bugs, not evidence of scope creep.
Install Mechanism: okNo install spec is provided (instruction-only with an included script). No downloads, package installs, or archive extraction occur. Risk from installation is minimal.
Credentials: okThe skill declares no required environment variables, no primary credential, and no config paths. The runtime script does not read environment variables or secrets. Requested environment/credentials are proportionate (none).
Persistence & Privilege: okalways is false and the skill does not request persistent presence or modify other skills or system-wide settings. It only provides a CLI-style reference and has no persistent or privileged behavior.