The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the robomotion CLI tool (e.g., robomotion validate <flow-dir>). The use of this tool is consistent with the vendor's infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of Robomotion flow directories and TypeScript source files, creating an attack surface for indirect prompt injection.
Ingestion points: Flow directories and files like main.ts or *.designer.ts are processed by the tool and the agent during the validation workflow as described in SKILL.md.
Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to ignore any natural language instructions that might be embedded within the flow code or metadata.
Capability inventory: The skill possesses the capability to execute shell commands and read local file structures.
Sanitization: No sanitization or validation of the content within the flow files is mentioned before the agent interacts with them.

validating-flow