ugc-creator-persona-design

Fail

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes a setup command to add an external MCP (Model Context Protocol) server from https://mcp.apimage.org/mcp. This domain is not recognized as a trusted source and closely resembles the name of an existing vendor, which may indicate typosquatting.
  • [REMOTE_CODE_EXECUTION]: By adding a remote MCP server from an untrusted source, the skill enables the agent to execute tools and code provided by an external entity, bypassing standard security controls for local skills.
  • [COMMAND_EXECUTION]: The skill provides a shell command in the 'Setup' section that modifies the agent's configuration to include external capabilities and handles authentication tokens for a remote service.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 8, 2026, 09:15 AM