prototype
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository files that could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Reads repository-local files including AGENTS.md, CLAUDE.md, design/gdd/game-concept.md, and production/review-mode.txt.
- Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore instructions embedded within the ingested data.
- Capability inventory: The skill utilizes Write, Edit, Bash, and Task tools, granting it the ability to modify files and execute system commands.
- Sanitization: Absent; no input validation or escaping is applied to the content read from external files before it is processed.
- [COMMAND_EXECUTION]: The skill executes shell commands using the Bash tool to perform Unity automation, project setup, and build validation tasks as part of its core prototyping functionality.
Audit Metadata