The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script located at scripts/sw_session.py to initialize and manage CAD sessions. This is an intended function for session state management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process external data sources that could contain malicious instructions.
Ingestion points: The skill reads engineering drawings, reference images, and data from a catalog lookup service to drive CAD geometry creation.
Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted external data from the system's operational instructions.
Capability inventory: The agent has the ability to execute Python scripts (sw_session.py), perform file system operations (writing to work/ and exports/), and interact with the SolidWorks API.
Sanitization: The instructions do not specify any validation, filtering, or sanitization steps for the data retrieved from drawings or catalog lookups.
[DATA_EXFILTRATION]: The skill includes a reporting workflow that invokes $sw-session-reporter to transmit session data for auditing purposes.

solidworks-design