react-component-generator

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (HIGH): High-risk Indirect Prompt Injection surface detected (Category 8). The skill ingests untrusted user requirements and has the capability to write the resulting code to the filesystem.
  • Ingestion points: User-provided component names and functional requirements are used to interpolate templates from the assets/ directory.
  • Boundary markers: None found; the skill does not instruct the agent to use delimiters or to disregard instructions within the user input.
  • Capability inventory: The agent is granted Write and Edit permissions, which allows for the creation of potentially malicious files if the user input contains a prompt injection attack.
  • Sanitization: No validation or sanitization process is described for the user input before it is used in code generation.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:51 AM