Skill Finder (Find ClawHub skills + Search Skills.sh)

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: skill-finder Version: 1.1.5 The 'skill-finder' bundle is a utility designed to help AI agents discover and install additional capabilities from the ClawHub and Skills.sh registries. The logic is entirely consistent with its stated purpose, and the SKILL.md instructions include explicit security constraints, such as forbidding the use of force-install flags (-y) and requiring user consent before installation. It manages local state in a dedicated directory (~/skill-finder/) and provides structured evaluation criteria (evaluate.md) to help the agent avoid low-quality or outdated packages.

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.

What this means

If the user approves an install, the agent may gain new behavior from another skill.

Why it was flagged

The skill can guide the agent to use external CLI tools and install new skills, which changes the agent environment; the same text also discloses review and opt-in safeguards.

Skill content
This skill uses `npx clawhub` and `npx skills` to discover and install skills from two different ecosystems. Review candidates before installation, keep installs opt-in
Recommendation

Review the recommended skill, its source, and scanner status before approving installation.

What this means

A poorly maintained or misleading third-party skill could be recommended if evaluation is not done carefully.

Why it was flagged

The skill intentionally works with an external open skill ecosystem, so source provenance and exact install strings matter.

Skill content
For `Skills.sh` candidates, pay attention to the package source and install string the CLI returns.
Recommendation

Prefer clear, maintained, reputable sources and avoid installing ambiguous Skills.sh or ClawHub results.

What this means

Saved preferences and liked/passed skill history may affect future recommendations.

Why it was flagged

The skill persists preference memory that will influence later recommendations, but the storage location and intended contents are disclosed.

Skill content
This skill stores local preference data in `~/skill-finder/`: - Source mode, explicit preferences, liked skills, and passed skills
Recommendation

Keep only non-sensitive preference information in this memory file and review it if recommendations seem biased or stale.

What this means

Future skill-related requests may automatically use this skill and its local memory.

Why it was flagged

The setup guidance can add persistent routing so the skill and its memory are loaded for future skill-related requests; it is scoped and disclosed, not hidden background behavior.

Skill content
When a request sounds like finding, comparing, or installing a skill, always load the `skill-finder` skill and `~/skill-finder/memory.md` before answering.
Recommendation

Only add the AGENTS.md routing line if you want this persistent behavior, and remove it later if you prefer manual invocation.