re-anti-cheat

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard Windows diagnostic utilities such as driverquery, sc query, and fltmc to enumerate system components. These commands are used for legitimate discovery of anti-cheat drivers and services within the researcher's environment.
  • [EXTERNAL_DOWNLOADS]: The skill references the Sysinternals utility suite from the official Microsoft domain. This is a reference to a well-known service from a trusted organization and is standard practice for system analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading and analyzing output from system commands and kernel debuggers, which constitutes an ingestion point for untrusted data from the target system being analyzed.
  • Ingestion points: Output streams from driverquery, sc query, fltmc, and debugger logs from WinDbg as described in SKILL.md.
  • Boundary markers: The skill does not explicitly define delimiters for separating analyzed data from agent instructions.
  • Capability inventory: The skill has access to shell command execution and kernel-level analysis tools.
  • Sanitization: No specific sanitization or filtering logic is described for the data ingested from the analyzed system components.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 02:17 PM