game-ai

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it is designed to read and interpret the contents of an untrusted codebase.
  • Ingestion points: The skill scans all files in the current directory or paths provided in arguments (Phase 1-7).
  • Boundary markers: Absent. There are no instructions for the agent to use delimiters or to disregard instructions found within the analyzed files.
  • Capability inventory: The skill primarily performs file read operations and a single file write for telemetry. It does not possess network access or arbitrary command execution capabilities.
  • Sanitization: Absent. The skill does not implement escaping or validation for the content it reads from the target codebase.
  • [COMMAND_EXECUTION]: The skill generates a report that suggests running other commands (e.g., /game-performance, /level-design). While these are just recommendations for the user and not automated execution, they represent a tool-chaining pattern common in integrated agent environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:56 AM
Security Audit — agent-trust-hub — game-ai