skills/dslsdzc/rev-skills/re-console/Gen Agent Trust Hub

re-console

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for installing reverse engineering tools using system package managers such as apt, brew, pacman, and dnf across different operating systems.
  • [EXTERNAL_DOWNLOADS]: The guide directs the user to fetch the hactool utility from a public GitHub repository and suggests downloading emulators from their official websites (mgba.io, fceux.com). These are recognized as standard community tools for the tasks described.
  • [DYNAMIC_EXECUTION]: Instructions are provided to compile the hactool utility from source using make on Unix-like systems and to develop custom analysis scripts utilizing the pyelftools Python library.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and interpret external data from console binary containers and game ROMs, which presents a surface for indirect prompt injection attacks.
  • Ingestion points: The agent is expected to analyze files such as target.bin, main.nso, and various .gba or .sav files using specialized tools (SKILL.md).
  • Boundary markers: The skill lacks specific instructions or delimiters to isolate the content of analyzed files from the agent's internal instruction set.
  • Capability inventory: The agent can execute file system and container analysis commands, which could be subverted if a processed file contains hidden instructions.
  • Sanitization: No specific data sanitization or escaping mechanisms are described for the output generated by the analysis tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:04 AM