ios-debugger-agent

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill contains no detected malicious patterns, obfuscation, or unauthorized data exfiltration.
  • [COMMAND_EXECUTION]: The skill uses XcodeBuildMCP tools (e.g., mcp__XcodeBuildMCP__build_run_sim) to execute commands for listing simulators, building projects, and launching applications. These actions are within the expected scope of an iOS development tool.
  • [DATA_EXFILTRATION]: The skill accesses project paths and captures application logs/screenshots. This information is processed locally for debugging purposes and is not transmitted to non-whitelisted external domains.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from application logs and UI descriptions. While this provides a potential surface for indirect prompt injection, the skill lacks autonomous high-privilege capabilities that would enable an exploit to move beyond the agent's internal reasoning context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 03:11 AM
Security Audit — agent-trust-hub — ios-debugger-agent