behavior-tree-generation
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural-language scenarios to generate behavior trees, creating a surface for indirect prompt injection.
- Ingestion points: The
scenarioparameter in thegenerate_behavior_treefunction (SKILL.md, references/api-and-inputs.md). - Boundary markers: The skill does not explicitly describe the use of boundary markers or instructions to ignore embedded commands within the user-provided scenario text.
- Capability inventory: The skill generates behavior tree files that are subsequently executed by the Replicator Agent (
isaacsim.replicator.agent) to control character or robot groups. - Sanitization: There is no documentation regarding the sanitization or validation of the natural-language input before it is passed to the LLM-driven planner.
Audit Metadata