visual-asset-generator

Warn

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of an external package prompt-to-asset from the npm registry. This package is not from a known trusted source or well-known service.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to install software globally (npm install -g prompt-to-asset).
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from local project files to generate prompts.
  • Ingestion points: Reads the project README and existing brand assets (SKILL.md).
  • Boundary markers: None present to separate project data from generation instructions.
  • Capability inventory: Calls the prompt-to-asset MCP server and writes files to assets/, public/, or src/assets/.
  • Sanitization: No validation or sanitization of ingested text before it is used in the prompt engineering process.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 15, 2026, 01:40 AM
Security Audit — agent-trust-hub — visual-asset-generator