skills/logicober/worldview-skills/worldview-game-character-handoff-and-shared-evidence/Gen Agent Trust Hub
worldview-game-character-handoff-and-shared-evidence
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of design guidelines, templates, and examples for managing character handoffs in narrative-driven games. It does not introduce any third-party dependencies or remote code execution risks.
- [INDIRECT_PROMPT_INJECTION]: The skill involves analyzing external project assets (source code, save files, quest logs), which presents a surface for indirect prompt injection from untrusted project content.
- Ingestion points: Project source files, runtime data, and game state records (quest logs, journals) as specified in
SKILL.md. - Boundary markers: The skill does not define specific text delimiters or 'ignore' instructions for external data, relying instead on a design 'Lock sequence' to verify data integrity.
- Capability inventory: The agent is authorized to read filesystem data, modify project code, and interact with the project runtime environment to validate implementations.
- Sanitization: No specific input sanitization or filtering of external data content is described in the instructions.
- [COMMAND_EXECUTION]: The skill directs the agent to inspect project structures and validate builds. These actions are performed using the agent's existing capabilities for local development and do not involve high-risk commands or privilege escalation.
Audit Metadata