ios-debugger-agent
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources within the iOS simulator environment.
- Ingestion points: The agent reads application logs via
mcp__XcodeBuildMCP__start_sim_log_capand UI metadata/element labels viamcp__XcodeBuildMCP__describe_uias specified inSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore or sanitize instructions that might be embedded within the app logs or UI strings.
- Capability inventory: The skill has powerful capabilities including building/running code (
mcp__XcodeBuildMCP__build_run_sim) and simulating user input (mcp__XcodeBuildMCP__tap,mcp__XcodeBuildMCP__type_text). - Sanitization: There is no evidence of sanitization or validation for the content retrieved from the simulator before it is processed by the agent.
Audit Metadata