ios-debugger-agent
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows secure interaction patterns by verifying the environment before execution and requiring user confirmation before booting hardware simulators. No indicators of exfiltration, obfuscation, or unauthorized access were found.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests untrusted data from the iOS simulator environment (logs and UI metadata). While this is necessary for the skill's primary purpose of debugging, it constitutes a potential vector for malicious app content to influence agent logic. Ingestion points: Application logs captured via mcp__XcodeBuildMCP__start_sim_log_cap and UI trees from mcp__XcodeBuildMCP__describe_ui (SKILL.md). Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore or delimit instructions found within captured logs or UI labels. Capability inventory: Tool-mediated interactions for building (build_run_sim), launching (launch_app_sim), and UI interaction (tap, type_text, gesture) across all scripts. Sanitization: Absent; the skill does not define filtering or validation for the content read from the simulator.
Audit Metadata