xcode-build-benchmark
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
xcodebuildand a local Python helper script (scripts/benchmark_builds.py) to perform repetitive build measurements. These commands are typical for build performance tooling. - [INDIRECT_PROMPT_INJECTION]: The skill acts on data parsed from external project files, such as scheme names and Swift Package Manager manifests.
- Ingestion points: External project metadata, workspace paths, and SPM
exclude:paths. - Boundary markers: None specified for the interpolation of project data into shell commands.
- Capability inventory: The skill possesses the capability to execute shell commands and create directories on the filesystem.
- Sanitization: The instructions do not mandate validation or sanitization of input gathered from the project environment.
Audit Metadata