code-game-trailer
Warn
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The
scripts/director-runtime.jsfile contains a utility functionev = (expr) => (typeof expr === 'string' ? (0, eval)(expr) : expr)which useseval()to execute strings provided in thedirector.jsonconfiguration file. This is used to resolve references to the game's renderer, camera, and internal state at runtime. - [COMMAND_EXECUTION]: Multiple scripts (
capture.ts,cut.ts,check.ts,beats.ts) useBun.spawnto execute shell commands forffmpeg,ffprobe,magick, andchrome. These operations are used for frame capture, audio analysis, and video encoding. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the
director.jsonfile, which serves as a control surface for the agent's actions. - Ingestion points: The
director.jsonfile, specifically fields such asready,probe,setup,hooks, andcamera.space, which are treated as executable JavaScript expressions. - Boundary markers: None identified; expressions are evaluated directly within the browser session.
- Capability inventory: The skill possesses capabilities for file system writes via
Bun.write, arbitrary command execution viaBun.spawn, and browser interaction through a custom CDP client. - Sanitization: There is no sanitization or validation of the expressions provided in the configuration file before they are passed to
eval().
Audit Metadata