hytopia-plugins

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill encourages the installation and use of third-party libraries via NPM.
  • Evidence: The 'Installing Plugins' section provides commands for npm install, bun add, and yarn add using lodash as an example.
  • Risk: This introduces a dependency on the public NPM registry, which can be a vector for supply chain attacks if a user or the agent specifies a malicious package name.
  • [COMMAND_EXECUTION] (LOW): The skill provides explicit shell commands for the agent to use or recommend.
  • Evidence: Code blocks in 'Installing Plugins' section include bash commands for package managers.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill creates an attack surface by processing user requests for external content (NPM packages).
  • Ingestion points: User prompts requesting the addition of specific plugins or packages.
  • Boundary markers: Absent. The skill does not provide instructions for the agent to validate or sanitize package names before suggesting installation.
  • Capability inventory: The agent is given the capability to suggest or facilitate the execution of package installation commands.
  • Sanitization: None specified in the instructions for the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 08:00 AM