underworld-overseer-save-mapper
Warn
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
scripts/setup.shscript performs agit clonefrom a remote repository (github.com/RobThePCGuy/Underworld-Overseer-Save-Mapper) that is not associated with a verified service or the skill author. - [REMOTE_CODE_EXECUTION]: The skill instructions direct the agent to execute the
main.pyscript contained within the third-party repository after the installation process is complete. - [COMMAND_EXECUTION]: The skill uses shell commands in
scripts/setup.shto install environment dependencies usingpipand manage the repository clone. - [PROMPT_INJECTION]: The skill processes untrusted JSON data from game save files, creating a surface for indirect prompt injection.
- Ingestion points: The
scripts/validate_save.pyscript and the externalmain.pyread user-provided JSON save files from the local filesystem. - Boundary markers: The
SKILL.mdinstructions include a mandatory pre-validation step usingscripts/validate_save.pyto identify structural anomalies before the data is passed to the renderer. - Capability inventory: The agent has the capability to execute shell commands (
SKILL.md), clone repositories (scripts/setup.sh), and run Python scripts (scripts/validate_save.py). - Sanitization: The
scripts/validate_save.pyscript performs type checking, ensuring coordinates are integers and identifying duplicate entries, which helps mitigate basic data malformation attacks.
Audit Metadata