find-skills

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute npx skills find and npx skills add commands. These are legitimate operations for the skill's purpose of managing agent extensions via the official CLI tool.- [EXTERNAL_DOWNLOADS]: The skill facilitates downloading skills from external sources, specifically referencing vercel-labs/agent-skills. As Vercel Labs is a well-known and trusted organization, these references are considered safe under standard operating procedures. The skill also references skills.sh, which is the official portal for this ecosystem.- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, obfuscation, or persistence mechanisms were detected. The use of -y and -g flags in the installation command is documented as a standard way for the agent to automate the setup process for the user upon request.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:35 AM