game-ui-component-breakdown
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple YAML contract files, which are used to construct instructions for subsequent generation tasks.
- Ingestion points: Reads from
contracts/style-contract.yaml,contracts/screen-contract.yaml,contracts/component-contract.yaml, andcontracts/asset-manifest.yaml. - Boundary markers: No explicit delimiters or warnings are used to isolate contract data from the agent's instructions.
- Capability inventory: The skill writes markdown files to the
prompts/components/directory and invokes thegame-ui-sprite-sheet-splittertool. - Sanitization: There is no evidence of sanitization or strict schema validation for the external contract data before interpolation.
- [DYNAMIC_EXECUTION]: The skill dynamically generates markdown files using predefined templates. These files serve as instruction sets for further AI processing, categorizing this as low-severity script generation.
Audit Metadata