ios-debugger-agent
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the iOS simulator environment, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The agent is directed to read and summarize content from simulator logs (
mcp__XcodeBuildMCP__start_sim_log_cap), build error messages, and UI hierarchy descriptions (mcp__XcodeBuildMCP__describe_ui) as specified in the 'Core Workflow' and 'Logs' sections ofSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or 'ignore embedded instructions' warnings for the data ingested from the simulator, which may lead the agent to follow commands embedded in logs or UI labels.
- Capability inventory: The agent has the authority to execute builds, launch applications, and perform UI interactions like tapping and typing (
mcp__XcodeBuildMCP__tap,mcp__XcodeBuildMCP__type_text), providing a functional path for injected instructions to take action. - Sanitization: There is no evidence of input validation or sanitization for the data retrieved from the simulator environment before it is analyzed by the agent.
Audit Metadata