mod-any-game
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the universal-modder toolkit from the author's GitHub repository (github.com/rehan-remade/universal-modder). This toolkit is a vendor-owned resource used for engine reconnaissance, asset conversion, and automation.
- [REMOTE_CODE_EXECUTION]: Instructions guide the agent to install and execute code from remote sources using package managers like uv or pipx. This includes the author's primary toolkit and various engine-specific community tools mentioned in the reference documentation.
- [COMMAND_EXECUTION]: The skill utilizes a CLI tool (um) to perform system-level operations, including scanning local directories for game installations, managing file backups, capturing media via window-specific handles, and interacting with running game processes.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it instructs the agent to ingest and process untrusted external data, such as game logs (client.log, Player.log), community-authored wikis, and decompiled source code.
- Ingestion points: Game log files, knowledge base search results, and external community documentation.
- Boundary markers: No explicit markers are defined for the data processed by the toolkit.
- Capability inventory: The agent can execute commands, write to the filesystem, and record the screen via the um tool.
- Sanitization: The skill includes a publish check utility to scan for secrets in mod files before sharing, though it does not explicitly sanitize inbound data for prompt injection.
Audit Metadata