Clawhub
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A mistaken or unreviewed bulk update could change how the agent behaves in later sessions.
The skill documents a command that can update all installed skills, which is a broad mutation of the agent's local skill environment. It is purpose-aligned and presented as a user-directed command, not hidden automation.
clawhub update --all
Run install or update commands only when requested, confirm the target slug or bulk update scope, and review skill changes before enabling them.
Installing or trusting an external CLI and third-party skills introduces normal supply-chain risk.
The skill relies on an external globally installed npm CLI that is not bundled or pinned in the provided artifacts. The instruction says to ask the user to install it manually and not auto-install without confirmation.
npm i -g clawhub
Install the CLI only from a trusted source, keep it updated intentionally, and review ClawHub skill contents before installing or updating them.
A bad or unintended skill install could influence future OpenClaw sessions until removed or changed.
The artifacts disclose that installed workspace skills can override other skills and will be picked up in a new session, so one installed skill can affect future agent behavior.
Workspace skills (`<workspace>/skills/`) take highest precedence over managed and bundled skills
Treat installed skills as persistent configuration, review them before enabling, and remove or update any skill that behaves unexpectedly.