unity-prefab

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes a potential surface for indirect prompt injection by processing external data via JSON strings to drive batch operations.
  • Ingestion points: The 'items' parameter in 'prefab_instantiate_batch' and the 'steps' parameter in 'prefab_edit_batch' ingest JSON-formatted instruction sets.
  • Boundary markers: No explicit delimiters or boundary markers are defined in the skill documentation to isolate these inputs from the agent's internal reasoning.
  • Capability inventory: The skill possesses file-writing capabilities (modifying '.prefab' assets) and the ability to manipulate Unity scene states.
  • Sanitization: The documentation mentions internal validation, such as rejecting invalid inherited structures and specific script/bookkeeping property writes.
  • [DYNAMIC_EXECUTION]: The 'prefab_edit_batch' tool implements a form of dynamic command execution by interpreting an ordered list of operations provided in a JSON array. While restricted to a set of allowed Unity-specific operations, it allows for the programmatic assembly of asset modifications at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 02:25 AM