defold-scripts-editing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the use of a third-party dependency defold-utf8 and provides a direct download link to a ZIP archive from a personal GitHub repository (https://github.com/d954mas/defold-utf8/archive/refs/heads/master.zip).
  • [COMMAND_EXECUTION]: Documentation in references/editor_script.md describes the editor.execute() function, which is used to run external commands and processes from the editor.
  • [INDIRECT_PROMPT_INJECTION]: The skill serves as a template and guide for generating Lua code, which creates a potential surface for indirect prompt injection.
  • Ingestion points: The agent ingests user-provided logic and existing file content to generate or modify .script, .lua, and other Defold-specific files.
  • Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following malicious instructions embedded in the data it processes.
  • Capability inventory: The agent has the capability to write to the local filesystem (editing scripts) and provides information on how to utilize system execution APIs (editor.execute).
  • Sanitization: There are no built-in sanitization routines or validation checks for the code being produced.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:23 PM
Security Audit — agent-trust-hub — defold-scripts-editing