audit-xcode-security-settings

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill reads untrusted project files such as .pbxproj, .xcconfig, and .entitlements to inform its security audit and decision-making process.
  • Ingestion points: Reads various project configuration files and existing xcode-security-settings.md decision documents via XcodeRead.
  • Boundary markers: Content from these untrusted files is interpolated into the agent's context without explicit delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill can modify project settings through UpdateProjectBuildSetting and UpdateTargetBuildSetting, and execute shell commands via plutil.
  • Sanitization: No specific sanitization or validation of the project file content is defined in the instructions.
  • [COMMAND_EXECUTION]: Local Shell Command Execution. The skill uses the plutil utility for property list manipulation and workspace configuration, as well as git for repository management when standard tools are insufficient. These operations are intended for project hardening and are clearly documented in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:29 PM
Security Audit — agent-trust-hub — audit-xcode-security-settings