ios-debugger-agent
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill triggers build and run processes on the local machine using Xcode tools. This is the core functionality and is used as intended by the user.
- [DATA_EXPOSURE] (SAFE): While the skill captures simulator logs and screenshots, this data is used for debugging purposes within the session. No network exfiltration patterns to non-whitelisted domains were identified.
- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection. 1) Ingestion points: reads logs via mcp__XcodeBuildMCP__start_sim_log_cap and UI state via mcp__XcodeBuildMCP__describe_ui. 2) Boundary markers: None. 3) Capability inventory: can execute build commands and UI interactions. 4) Sanitization: None. This is a standard risk for debugging tools processing external output.
Audit Metadata