skills/dojoengine/book/dojo-token/Gen Agent Trust Hub

dojo-token

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADS
Full Analysis
  • [External Downloads] (MEDIUM): The skill recommends adding the origami_token dependency via a direct Git URL: https://github.com/dojoengine/origami. The dojoengine organization is not included in the predefined list of trusted GitHub organizations.
  • [External Downloads] (MEDIUM): The JavaScript examples utilize the @dojoengine/sdk package. While provided as a standard integration, this package originates from an untrusted source relative to the security policy.
  • [Indirect Prompt Injection] (LOW): The skill has the capability to read and modify configuration files (Scarb.toml, torii.toml, dojo_dev.toml) and execute shell commands (sozo, torii).
  • Ingestion points: Project configuration files and command-line outputs from the Dojo toolchain.
  • Boundary markers: Absent; the skill does not define specific delimiters for separating untrusted configuration data from instructions.
  • Capability inventory: Includes Bash (command execution), Write/Edit (file modification), and Read (file access).
  • Sanitization: No explicit sanitization or validation of external configuration data is mentioned before processing or execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:10 PM