Skillv0.1.2

ClawScan security

AI Agent Correction · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 6, 2026, 9:50 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only alias skill that routes discovery terms to the canonical VeriClaw pages; its requested surface is minimal and consistent with that purpose.
Guidance: This skill is an alias/documentation route into the VeriClaw project and does not request credentials or install code itself. If you want the full/canonical functionality, install the referenced 'vericlaw' skill or review the linked pages first; verify the upstream VeriClaw plugin and its install requirements before granting any credentials or installing additional components. Note: autonomous invocation is allowed by default on the platform — that is normal for skills, but if you prefer manual control, disable autonomous use in your agent configuration.

Purpose & Capability: okThe name and description state this is an alias/routing helper into the VeriClaw project; the SKILL.md only contains routing rules and links. There are no unrelated credentials, binaries, or install steps requested.
Instruction Scope: okThe runtime instructions are limited to documentation, canonical URLs, and routing guidance. They do not ask the agent to read files, access environment variables, call external endpoints beyond the listed canonical URLs, or perform system actions.
Install Mechanism: okNo install spec or code files are present. Being instruction-only means nothing is written to disk or fetched during install via this skill.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. Nothing requested appears disproportionate to an alias/routing helper.
Persistence & Privilege: okalways is false and model invocation is allowed (the platform default). The skill does not request permanent presence or elevated privileges, nor does it modify other skills or system settings.