game-help

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill automatically ingests and processes data from external project files to provide recommendations, creating a potential vector for malicious instructions to be introduced into the agent's context.
  • Ingestion points: The skill reads .gameforge/project.json, project.godot, ProjectSettings/ProjectVersion.txt, *.uproject, and package.json from the local workspace.
  • Boundary markers: The instructions do not define delimiters or specific "ignore embedded instructions" warnings when reading these files.
  • Capability inventory: The skill utilizes Read, Glob, and Grep to gather data, but its primary output is advising the user on which other skills to run via AskUserQuestion or markdown text.
  • Sanitization: There is no evidence of sanitization or strict schema validation for the contents of the files being read.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 02:57 AM