skill-discovery

Warn

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides commands to download and install content from external GitHub repositories via the npx skills add command. While it mentions trusted sources like Vercel Labs, the core functionality allows the agent to pull in code from any arbitrary repository listed in the marketplace.
  • [REMOTE_CODE_EXECUTION]: The workflow involves fetching and executing remote scripts from community sources. The documentation explicitly instructs the agent to use the --yes flag to skip interactive prompts (e.g., npx skills add owner/repo@skill --yes), which removes human review from the installation of executable code.
  • [COMMAND_EXECUTION]: The skill uses the npx utility to execute shell commands for discovering and managing tools. These commands perform system-level operations, such as creating symlinks and installing files into the user's home directory at ~/.agents/skills/.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 17, 2026, 05:19 PM
Security Audit — agent-trust-hub — skill-discovery