gunpla-poster
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is a pure instruction set (SKILL.md) with no executable scripts, binaries, or configuration files.
- [SAFE]: No patterns of data exfiltration, credential theft, or unauthorized network access were identified.
- [SAFE]: The skill implements a state-based interview to gather user preferences, which are then used to build an image generation prompt. This controlled workflow minimizes the risk of unintended behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to construct image prompts. While this represents a data ingestion surface, the risk is mitigated by the agent's instructions to refine and translate inputs, as well as the inclusion of negative constraints in the final template. Ingestion points: User input for mobile suit, framing, pose, environment, and ratio. Capability: Image generation tool. Sanitization: Agent-led refinement and translation.
Audit Metadata