skills/udecode/plate/test-xcode/Gen Agent Trust Hub

test-xcode

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the xcodebuildmcp package from the NPM registry. This is the core dependency required for the skill to function and is a standard external resource for this development context.
  • [COMMAND_EXECUTION]: The skill uses specialized MCP tools to interact with the local filesystem and the Xcode toolchain (xcodebuild, simctl). These commands are necessary for the primary purpose of building and testing mobile applications.
  • [PROMPT_INJECTION]: The skill reads simulator logs (mcp__xcodebuildmcp__get_sim_logs), which is an ingestion point for untrusted data from the app being tested. This represents an indirect prompt injection surface.
  • Ingestion points: Raw system and application logs from the booted simulator.
  • Boundary markers: None present to delimit untrusted log data from agent instructions.
  • Capability inventory: The agent can create markdown-based todo files and suggest code modifications based on logs.
  • Sanitization: Log data is analyzed directly without pre-processing or sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 05:26 PM