xcodebuildmcp
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes tools that ingest data from external sources, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill performs log capture from simulators and devices and inspects UI view hierarchies (SKILL.md).
- Boundary markers: There are no instructions to use specific delimiters or to treat the ingested data as untrusted text to prevent the agent from following embedded instructions.
- Capability inventory: The environment supports high-privilege operations including code compilation, application execution, debugger attachment via LLDB, and UI automation (gestures, hardware button presses, and text input).
- Sanitization: The instructions do not define any sanitization or validation steps for content retrieved from external logs or UI inspections.
- [EXTERNAL_DOWNLOADS]: The skill references an external domain (
xcodebuildmcp.com) for configuration documentation. This URL is consistent with the skill's stated purpose.
Audit Metadata