xcodebuildmcp

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interfaces with Apple development command-line tools. The debug_lldb_command tool allows for arbitrary command execution within the LLDB debugger environment. Tools such as build_run_sim and swift_package_run facilitate the compilation and execution of local code.
  • [DATA_EXFILTRATION]: Tools like debug_variables, snapshot_ui, and log capture provide access to sensitive runtime data from the target application, including memory variables and UI hierarchies. While potentially sensitive, this is standard functionality for development tools.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to the ingestion of untrusted runtime data. 1. Ingestion points: snapshot_ui, debug_variables, and system/application logs. 2. Boundary markers: Absent in tool instructions. 3. Capability inventory: Subprocess execution for build and debug tasks. 4. Sanitization: Not specified for ingested runtime data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 07:10 PM