ios-debugger-agent
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze console logs and UI descriptions from an iOS simulator. These external sources are untrusted and could contain malicious instructions aimed at manipulating the agent.
- Ingestion points:
mcp__XcodeBuildMCP__describe_uiandmcp__XcodeBuildMCP__start_sim_log_capinSKILL.md. - Boundary markers: The instructions lack explicit delimiters or instructions to ignore commands embedded within the captured logs or UI labels.
- Capability inventory: The skill utilizes tools that can perform builds, launch applications, and simulate user interactions (taps, typing) on the host environment.
- Sanitization: There is no requirement for sanitizing, escaping, or validating the content captured from logs or UI inspections before processing.
Audit Metadata