Skill Downloader
Analysis
This is a coherent review-first helper for finding and installing OpenClaw skills, with the main user-visible risk being that approved installs or updates can change future agent behavior.
Findings (2)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Do not install or update anything without explicit user approval. When installing or updating: - use the requested destination (`~/.openclaw/skills/` for global or `{workspace}/skills/` for local by default)The skill can direct writes or updates to persistent skill directories, but the artifact clearly scopes the destinations and requires explicit approval.
Primary sources: - ClawHub - GitHub `anthropics/skills` - skills.sh
The workflow intentionally discovers candidates from external registries or repositories, which is expected for this purpose but makes candidate provenance and review important.
