skills/openai/plugins/build-run-debug/Gen Agent Trust Hub

build-run-debug

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill utilizes standard macOS developer tools such as xcodebuild, swift build, lldb, and open to build, run, and debug applications.
  • Dynamic Script Generation: It generates a project-local shell script (script/build_and_run.sh) based on templates to automate the build and launch cycle.
  • File Permission Modification: The skill uses chmod +x to make the dynamically created build script executable, which is necessary for the automation to function.
  • Indirect Prompt Injection Surface: Because the skill scans and interprets project files (like .xcodeproj or Package.swift) to configure its build commands, it has a surface area for indirect prompt injection if those files contain malicious metadata designed to influence agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:16 PM
Security Audit — agent-trust-hub — build-run-debug