game-assets
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
curl,wget, and various localnodescripts (e.g.,build-character.mjs,crop-head.mjs,build-spritesheet.mjs) to automate the asset creation pipeline. - [EXTERNAL_DOWNLOADS]: The skill fetches image assets, logos, and character photos from external sources. It directs the agent to download content from well-known asset repositories (Kenney.nl, OpenGameArt.org, itch.io) and from arbitrary URLs found in
thread.jsonor through WebSearch. - [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting untrusted data from external sources:
- Ingestion points: Data enters the context through
thread.json(image_urlfield) and WebSearch queries for personality photos and company logos. - Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions in external data are provided.
- Capability inventory: The skill has the capability to execute shell commands (
curl,node), write to the filesystem, and perform network downloads. - Sanitization: There are no explicit instructions for sanitizing or validating the input data before it is passed as arguments to shell commands.
Audit Metadata