dcl-prototype

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from user-authored hypothesis files which could contain instructions that influence agent behavior.
  • Ingestion points: The agent reads markdown files from the design/ directory, specifically design/*/H*_*.md and design/gdd.md.
  • Boundary markers: The skill relies on structured headers (e.g., ## Brief, ## Sessions) to parse content but does not include explicit instructions to disregard embedded commands or use sanitization.
  • Capability inventory: The skill has access to file system writes, shell command execution via npx, and local network probing of the scene preview port.
  • Sanitization: No methods for escaping or filtering instructions within the ingested data are mentioned.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage its environment and tools.
  • Evidence: references/greybox-build.md and references/bootstrap.md describe using npx skills add decentraland/sdk-skills --all and skills update.
  • Mitigation: The instructions contain security constraints requiring the agent to "ask the owner before installing" or launching the preview server.
  • [EXTERNAL_DOWNLOADS]: The skill references several external repositories for game assets and models.
  • Evidence: references/scene-resources.md provides links to kenney.nl, quaternius.com, polyhaven.com, ambientcg.com, and freesound.org.
  • Note: These sources are well-known and reputable services within the game development community.
  • [CREDENTIALS_UNSAFE]: The skill includes guidance to avoid exposing sensitive information during its operation.
  • Evidence: references/bootstrap.md explicitly states: "Keep tokens, credentials and copied MCP configs out of this note."
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 02:40 PM