monitoring-cpu-usage
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs analysis on application code and logs to identify performance bottlenecks. There is a potential attack surface where malicious content embedded in the code or logs being analyzed could influence agent behavior.
- Ingestion points: Files and directories processed by
scripts/cpu_analyzer.pyand JSON configuration files parsed byscripts/example_usage.py. - Boundary markers: No explicit boundary markers or "ignore instructions" delimiters are defined in the instructions.
- Capability inventory: The skill has broad capabilities including file writing, editing, and unrestricted bash execution (
Bash(cmd:*)). - Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill requests unrestricted bash access via the
allowed-tools: Bash(cmd:*)configuration. This level of access is necessary for the skill's stated purpose of profiling and monitoring system resources but grants the agent full shell control within the execution environment.
Audit Metadata