The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as find, test, and which to locate the Blender binary and its extension files.
[PERSISTENCE_MECHANISMS]: The setup workflow involves modifying user shell profiles (e.g., ~/.zshrc or ~/.bashrc) to add export and alias statements, ensuring the blendertorcp command persists across user sessions.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The agent processes output from searching the filesystem (e.g., results from find) and output from executing the verification script via python3 (found in SKILL.md).
Boundary markers: Absent; there are no instructions to treat the tool or search output as untrusted data.
Capability inventory: The agent has the capability to execute shell commands and write to system configuration files (found in SKILL.md).
Sanitization: Absent; the agent is not instructed to validate or sanitize paths or outputs discovered on the filesystem before using them to construct shell commands.

blendertorcp-setup