process-detection
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The documentation outlines the use of standard system utilities for process monitoring, such as
psandlsofon Unix, and PowerShell cmdlets likeGet-CimInstanceandGet-NetTCPConnectionon Windows. These operations are essential for the skill's primary purpose of auto-instrumentation and process discovery. - [INDIRECT_PROMPT_INJECTION]: The skill describes an architecture that ingests potentially untrusted data from the operating system, specifically process command lines and environment metadata, which serves as an attack surface for indirect injection.
- Ingestion points: Process listing commands including
ps ax(Unix) andGet-CimInstance Win32_Process(Windows) provide command-line strings to the agent context. - Boundary markers: The documentation does not specify the use of delimiters or specific instructions to ignore embedded content in command lines.
- Capability inventory: The system includes capabilities for process termination (
stopProcesses), process adoption (windows.OpenProcess), and active network polling (Get-NetTCPConnection). - Sanitization: The implementation uses case-insensitive substring matching and filtering (
strings.ToLower()) to correlate processes to projects, though specific prompt-level sanitization for ingested command strings is not detailed.
Audit Metadata