quick-game

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from external URLs (x.com, twitter.com) using a fetch-tweet tool to derive game concepts.
  • [COMMAND_EXECUTION]: Executes shell commands including npm install, npm run dev, and npm run build to scaffold and verify the game environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill abstracts game concepts from untrusted external data (tweet content) and passes this description into a Task subagent's prompt.
  • Ingestion points: Tweet content fetched via fetch-tweet (SKILL.md Step 0).
  • Boundary markers: None explicitly defined for the abstracted concept interpolation.
  • Capability inventory: Full file-system write access, subprocess execution (npm), and network access via tools.
  • Sanitization: None mentioned for the tweet-derived description before it is passed to the subagent.
  • [CREDENTIALS_UNSAFE]: Requests MESHY_API_KEY from the user for 3D asset generation; however, it asks the user to provide it rather than hardcoding it, which is standard behavior for API-dependent tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 03:51 PM