skills/aeondave/malskill/neuromatrix/Gen Agent Trust Hub

neuromatrix

Warn

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides tools for executing arbitrary shell commands and processes within the provider runtime.
  • Evidence: The spawn_endpoint_client tool allows the agent to execute a specified command with provided args and variables. Examples in references/debugging-and-composition.md show the use of /bin/sh to execute shell strings.
  • Evidence: The start_interactive_session tool allows launching interactive processes in the session workspace, such as emulators or debugger instances.
  • [REMOTE_CODE_EXECUTION]: The primary purpose of the skill is to execute user-provided code (binaries, firmware, kernels) across various emulation backends.
  • Evidence: The skill facilitates running binaries through backends including Unicorn, Qiling (userland binaries), QEMU (Linux user-mode and full-system), and Renode (MCU firmware).
  • Evidence: The import_artifact_to_workspace tool allows marking uploaded artifacts as executable (executable=true) before they are run by server-side tools.
  • [EXTERNAL_DOWNLOADS]: The skill uses a data plane that involves transferring potentially large files to and from external URLs.
  • Evidence: references/artifacts-jobs-endpoints.md describes a flow where request_upload and request_download return dynamic HTTP URLs for moving artifacts using curl or similar tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from emulated targets which could influence the agent's behavior.
  • Ingestion points: The agent reads data via read_interactive_session (UART/stdout from targets), inspect_binary, and analyze_artifact (SKILL.md).
  • Boundary markers: No explicit instructions are provided to the agent to treat emulation output or disassembly as untrusted or to use strict delimiters.
  • Capability inventory: The skill has high-privilege capabilities including command execution (spawn_endpoint_client) and file management (request_upload).
  • Sanitization: There is no mention of sanitizing or escaping the output from interactive sessions before the agent processes it.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 5, 2026, 10:40 PM
Security Audit — agent-trust-hub — neuromatrix