skills/egorfedorov/slot-casino-game-developer-skills-for-stake-engine/ai-game-designer/Gen Agent Trust Hub
ai-game-designer
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external JSON data that could contain instructions intended to influence the agent's behavior during the validation or design process.\n
- Ingestion points: The tool
scripts/validate_game_design_spec.pyreads local files provided via a command-line argument and processes their contents.\n - Boundary markers: The script does not use specific delimiters or instructions in its output summary to separate its own analysis from the data content found in the input file.\n
- Capability inventory: The skill allows the agent to read local files and execute Python validation logic, the results of which are then used to formulate further design steps.\n
- Sanitization: While the validation script enforces a specific JSON schema and data types, it does not sanitize the string content of fields like 'name' before including them in the final summary output.
Audit Metadata