game-generalist

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several scripts (record.mjs, contact-sheet.sh, av_markers.mjs) that execute external binaries ffmpeg and ffprobe using node:child_process.spawnSync. These tools are used for legitimate media processing tasks such as aligning audio-video tracks, generating contact sheets for visual review, and recording gameplay captures.
  • [DYNAMIC_EXECUTION]: The probe.mjs and record.mjs scripts dynamically import and utilize the Playwright library to automate browser environments. These scripts use page.evaluate to execute JavaScript in the game page context to read the window.__game hook, which is necessary for the automated playtest gates and recording functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection as it ingests and processes untrusted data from web pages during the playtesting phase.
  • Ingestion points: The targetUrl parameter in scripts/probe.mjs and scripts/record.mjs directs the agent to interact with arbitrary web content.
  • Boundary markers: No explicit prompt boundary markers or sanitization logic are present for the content of the pages being tested.
  • Capability inventory: The skill has the capability to execute browser scripts (page.evaluate) and shell commands (spawnSync for ffmpeg).
  • Sanitization: The skill does not perform specific sanitization of the data retrieved from window.__game.state(), though the risk is localized to the browser context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 02:24 AM