fastapi-router-creator

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The skill ingests untrusted user requests to generate code and configurations. It lacks boundary markers, delimiters, or sanitization logic to prevent malicious input from overriding instructions or manipulating shell commands.
  • Command Execution (INFO): The skill explicitly requests access to high-privilege tools including Bash, Write, and Edit. While appropriate for its stated purpose of backend development, these tools expand the attack surface if the agent is influenced by malicious input.
  • No Executable Code (INFO): No scripts or binaries are provided in this skill package; it consists solely of a descriptive markdown file defining agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:46 AM