skills/dcoon/agent-kit/npx-skills/Gen Agent Trust Hub

npx-skills

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the acquisition of content from external Git repositories and URLs through the npx skills add and npx skills use commands. This is the primary intended function of the skill for ecosystem management.
  • [COMMAND_EXECUTION]: Provides a series of shell commands using npx to interact with the local filesystem and environment, such as listing directories (ls ~/.agents/skills/), checking software versions (node --version), and executing the skills CLI tool.
  • [INDIRECT_PROMPT_INJECTION]: As a tool designed to find and install third-party instructions (skills), it creates an attack surface where an agent might ingest untrusted prompt content from external repositories. The skill includes a mitigating instruction to expect permission confirmation prompts before executing automated scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 11:23 PM