arthas-cpu-high
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a purely instructional markdown document designed to guide an AI agent through a standard performance diagnostic workflow using Arthas. It does not include any scripts, external dependencies, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill involves analyzing runtime application data which could potentially contain untrusted input that influences the agent's logic.
- Ingestion points: The skill instructs the agent to read and analyze
threadstack traces,watchmethod arguments/returns, andtt(Time Tunnel) diagnostic data from the JVM (SKILL.md). - Boundary markers: Absent; there are no instructions for the agent to distinguish between diagnostic data and potential embedded instructions.
- Capability inventory: The agent is guided to use internal diagnostic tools like
dashboard,thread,stack,trace,watch, andttto gather and report findings. - Sanitization: None provided; the agent processes raw output from the diagnostic tools to form its conclusion.
Audit Metadata