dayz-mcp-verify

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes PowerShell commands (e.g., Get-Item, Get-Process, Get-CimInstance, Stop-Process) and Python scripts to manage local test environments, monitor game processes, and interact with the dayz-mcp daemon on localhost.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and interpret game logs (script_*.log, RPT) for verification results, creating an indirect prompt injection surface if logs contain adversarial instructions.
  • Ingestion points: Game log files and bridge telemetry JSON are read via logs_since and telemetry_read respectively.
  • Boundary markers: Relies on specific pattern matching (e.g., wait_for(log_matches, "...")) to identify events without explicit escaping of content.
  • Capability inventory: Includes game world manipulation (spawn, teleport, delete), vehicle control, and UI interaction via the dayz-mcp toolset.
  • Sanitization: No specific sanitization of log content is instructed before the agent evaluates it for test outcomes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 08:17 AM