Find Skill

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This instruction-only skill is transparent about helping users find and install skills, but users should explicitly approve global installs and verify third-party sources.

This skill appears safe to use for discovery. Before letting it install anything, review the skill's source and owner, confirm you want a global user-level install, and be cautious with commands that skip confirmation prompts.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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

A selected skill could be installed into the user's global agent environment and affect future agent behavior.

Why it was flagged

This is a user-directed workflow, but it lets the agent run a global install command while bypassing the CLI's confirmation prompt.

Skill content
If the user wants to proceed, you can install the skill for them: `npx skills add <owner/repo@skill> -g -y`. The `-g` flag installs globally (user-level) and `-y` skips confirmation prompts.
Recommendation

Ask for explicit user approval before installing, show the exact package/source, and avoid `-y` unless the user has clearly approved skipping prompts.

What this means

Installing an untrusted skill could introduce unsafe instructions or tools into the user's agent setup.

Why it was flagged

The skill's core workflow depends on installing third-party skills from external sources. This is expected for the purpose, but provenance and trust still matter.

Skill content
`npx skills add <package>` - Install a skill from GitHub or other sources
Recommendation

Review the skill page, repository, owner, and permissions before installing any third-party skill.

What this means

Users may have a harder time confirming the exact package identity and version they are reviewing.

Why it was flagged

This packaged metadata differs from the supplied registry metadata, which lists a different owner ID, slug, and version. That is not malicious behavior by itself, but it creates a provenance/version clarity issue.

Skill content
"ownerId": "kn77ajmmqw3cgnc3ay1x3e0ccd805hsw", "slug": "find-skills", "version": "0.1.0"
Recommendation

The publisher should align registry and packaged metadata; users should verify they are installing the intended skill.