godot-resources

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for loading external resource files, which constitutes a data ingestion surface for potentially untrusted inputs.
  • Ingestion points: ResourceLoader.load() is described in SKILL.md and references/resource-patterns.md for loading configuration and level data.
  • Boundary markers: The skill mentions checking for file existence using ResourceLoader.exists() but does not provide guidance on validating the resource's integrity or origin.
  • Capability inventory: The skill includes patterns for file writing (ResourceSaver.save) and object instantiation from files (ResourceLoader.load).
  • Sanitization: No explicit sanitization or schema validation for the resource data is provided.
  • [DYNAMIC_EXECUTION]: The skill uses ResourceLoader.load() to dynamically load and instantiate resources, which in the Godot engine can include script logic and complex object hierarchies.
  • Evidence: SKILL.md (Pattern 4) and references/resource-patterns.md (Common API section) detail the dynamic loading of .tres and .res files at runtime, which is a form of dynamic asset instantiation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 09:05 PM