argent-ios-device-interact
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a guide for physical iPhone interaction, enumerating supported tools (such as list-devices, launch-app, and screenshot) and describing their operational constraints. The instructions do not include any malicious code, command execution, or data exfiltration patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill describes tools that ingest external UI data from the device screen (via describe and screenshot). This creates an ingestion surface for potentially untrusted content that could influence the agent. No boundary markers or sanitization protocols are defined in these instructions to mitigate this inherent surface risk.
Audit Metadata