touchdesigner-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
scripts/setup.shscript is configured to download an external TouchDesigner component (twozero.tox) fromhttps://www.404zero.com/pisang/twozero.toxusingcurl. - [COMMAND_EXECUTION]: The skill defines several tools that allow for command execution:
td_execute_pythonenables the agent to run arbitrary Python code within the TouchDesigner environment, which has full access to the local filesystem and the TouchDesigner API.td_input_executeallows the agent to send mouse and keyboard commands (clicks, typing, focus) to the TouchDesigner application.- [REMOTE_CODE_EXECUTION]: The
SKILL.mdinstructions guide the user to execute a local setup script (scripts/setup.sh) which performs network operations and modifies configuration files. - [DYNAMIC_EXECUTION]: The skill facilitates the dynamic generation and execution of code at runtime:
td_write_datandtd_execute_pythonare used to inject and run Python scripts and GLSL shaders into TouchDesigner operators.- The documentation in
references/glsl.mdandreferences/network-patterns.mdprovides templates for dynamic shader compilation and execution. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process data from various external sources.
- Ingestion points: Untrusted data enters the context through tools like
td_read_dat,td_read_chop, and networking operators described inreferences/external-data.md(WebSockets, MQTT, HTTP, and Serial). - Boundary markers: The instructions do not specify explicit delimiters or "ignore embedded instructions" warnings for data read from external sources.
- Capability inventory: The skill has extensive capabilities including arbitrary Python execution (
td_execute_python), UI automation (td_input_execute), and filesystem interaction within the host environment. - Sanitization: While
references/external-data.mdmentions basic validation for sensor data, there is no comprehensive sanitization logic described for handling potential instructions embedded in external network data.
Audit Metadata