gamedev-expert

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a mandatory 'Memory Protocol' that requires the agent to execute a shell command (cat .claude/context/memory/learnings.md) to read internal session history. While intended for context maintenance, this involves direct execution of commands on system-internal files.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the following surface:
  • Ingestion points: The skill reviews external source code files (DragonRuby, Ruby, Unity) for architectural and style compliance.
  • Boundary markers: No delimiters or instructions to disregard embedded directives in processed data are provided.
  • Capability inventory: The skill's allowed tools include Bash, Write, Edit, Read, Grep, and Glob, enabling extensive filesystem and command-line operations if malicious instructions are encountered in user-provided code.
  • Sanitization: No input validation or filtering is performed on the content being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:45 PM