spatial-app-perf-diagnose
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses
pico-cli, which is a vendor-owned resource associated with 'Pico-Developer'. The use of this CLI for device management, application inspection, and performance profiling (monitor, trace record, trace load) is appropriate for the skill's diagnostic purpose. - [SAFE]: The workflow includes strict 'interactive confirmation gates' (Gate 1 and Gate 2) that require the agent to present resolved capture parameters and commands to the user for confirmation or override before execution. This prevents the autonomous execution of potentially intrusive commands without user oversight.
- [SAFE]: Data ingestion is limited to local Perfetto trace files and JSON reports generated by the profiling tools. The skill follows a highly rigid analysis protocol using SQL queries and specific thread-state tallies, which significantly reduces the risk associated with indirect prompt injection from processed performance data.
- [SAFE]: No obfuscation, unauthorized privilege escalation, persistence mechanisms, or credential harvesting patterns were identified in the instructions or reference materials.
Audit Metadata