ui-convert-coordinator

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill acts as an orchestrator that processes untrusted project source code, creating an indirect prompt injection surface where malicious instructions in comments or code could influence the agent's behavior.
  • Ingestion points: Source files in the target project directory and metadata in .ui-convert/progress.json.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded content in the processed files.
  • Capability inventory: The skill orchestrates sub-skills with capabilities for file system writes and Model Context Protocol (MCP) tool execution.
  • Sanitization: No sanitization or validation of the ingested file content is described in the coordinator logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 08:01 PM
Security Audit — agent-trust-hub — ui-convert-coordinator