ui-components-expert
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to analyze and review user-provided UI component code while having access to sensitive tools like
Bash,Write, andEdit. This creates an indirect prompt injection vulnerability surface where an attacker could embed malicious instructions in code comments or metadata that the agent might inadvertently execute. - Ingestion points: User-provided source code and project files provided for review or refactoring (as indicated in SKILL.md capabilities).
- Boundary markers: The skill instructions do not define clear delimiters or provide directives to ignore instructions contained within the analyzed data.
- Capability inventory: Includes access to
Read,Write,Edit,Bash,Grep, andGlobtools across the skill context. - Sanitization: No sanitization or content validation of the input code is implemented before it enters the agent's context.
Audit Metadata