axiom-optimize-build

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from Xcode project files to determine build settings and optimization opportunities.
  • Ingestion points: Reads project configurations, targets, and build phases using xcproject inspect and searches for patterns in Package.swift and .xcodeproj files.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the project files being analyzed.
  • Capability inventory: The agent has the capability to run xcodebuild commands and use system utilities like sysctl, pgrep, and grep.
  • Sanitization: While the skill uses shell quoting for project-related variables, it does not perform deep validation of the contents of the project configuration files it processes.
  • [COMMAND_EXECUTION]: The skill uses system-level commands to perform build analysis and environment checks.
  • Evidence: Executes xcodebuild with custom compiler flags (-Xfrontend -debug-time-function-bodies) to generate timing data for functions and expressions.
  • Evidence: Uses sysctl -n hw.ncpu to determine available hardware resources and pgrep to monitor active build processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 08:48 PM