game-performance-profiler

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a diagnostic instruction set and does not contain executable scripts or remote code execution patterns. It utilizes a restricted set of tools (Bash, Read, Write, Edit) for processing data and generating reports. All external links point to official documentation from trusted organizations (Unity, Epic Games, AMD, Valve).\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external performance logs and user-provided feedback.\n
  • Ingestion points: Reads profiler captures, stat output, and user performance complaints via the agent tools (SKILL.md, references/profiling-patterns.md).\n
  • Boundary markers: Absent. The skill does not define specific delimiters for isolating untrusted data in its processing instructions.\n
  • Capability inventory: Uses Bash, Read, Write, Edit, Glob, and Grep. It can read and modify files in the working directory (SKILL.md).\n
  • Sanitization: Absent. The instructions do not specify any sanitization or validation of the ingested performance data before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 02:14 AM