inkos-play-world
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided narrative inputs and 'world contracts.' While this creates an ingestion surface for potential instructions embedded in user stories, the skill lacks any capabilities (such as file writing, network access, or command execution) that could be exploited through such an injection. It focuses entirely on text generation and state tracking within a narrative context.
- Ingestion points: User actions and world definitions in
SKILL.md. - Boundary markers: None explicitly defined.
- Capability inventory: Narrative text generation only; no dangerous tools identified.
- Sanitization: Not applicable as no external systems are modified.
- [SAFE]: No obfuscation, remote code execution, or credential exposure patterns were detected. The instructions are transparent and aligned with the stated purpose of narrative game management.
Audit Metadata