The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external simulation data, such as LAMMPS trajectories and other particle data, which creates a potential surface for indirect prompt injection if those files were to contain malicious instructions.
Ingestion points: LAMMPS trajectory files and particle data mentioned in SKILL.md and references/render-evidence.md.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from potentially following instructions embedded within the processed data.
Capability inventory: The skill utilizes the ai-cae-toolbox suite for environment configuration and run management.
Sanitization: The instructions do not specify any validation or sanitization steps for external data before it is parsed by the agent or visualization tools.
[COMMAND_EXECUTION]: The skill documentation includes specific usage of CLI tools for the simulation workflow.
Evidence: SKILL.md references the use of ai-cae-toolbox commands including context-scope, bridge-plan, create-run, and write-smoke-template to manage the lifecycle of a post-processing task.

ovito-evidence-postprocessing