skills/logicober/worldview-skills/worldview-game-runtime-visual-fidelity-rebuild/Gen Agent Trust Hub
worldview-game-runtime-visual-fidelity-rebuild
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze a user-provided game repository and its entry points. This creates a surface for indirect prompt injection where instructions hidden within the game's source code, asset metadata, or documentation could attempt to override the agent's behavior.
- Ingestion Points: The agent reads from the
repository pathand inspects theworktreeas described inSKILL.md. - Boundary Markers: The skill implements a 'Protected Behavior Lock' and a 'Protected-behavior contract' to strictly delimit visual changes from mechanical authority, which acts as a functional safeguard.
- Capability Inventory: The skill is authorized to patch repository files, coordinate external tools (DCC, Image APIs), and execute project-specific build/test commands.
- Sanitization: The workflow focuses on mechanical validation and regression testing to ensure behavioral consistency, but it does not explicitly specify sanitization of natural language instructions encountered within the processed project files.
Audit Metadata