cadcraft-cli
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill. It provides a standard set of instructions for interacting with a command-line tool.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform operations using the
cadcraft-clibinary. This execution is scoped to the skill's primary purpose of CAD file management and includes explicit warnings to use official distributions only. - [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface, as it involves reading and processing CAD files (DXF, DWG). Although processing external data is an inherent surface for indirect prompt injection, there are no specific instructions that would lead to the unsafe handling of untrusted content.
- Ingestion points: Processes external files like
drawing.dxfandinput.dxf(SKILL.md). - Boundary markers: Absent.
- Capability inventory: Executes subprocesses (
cadcraft-cli) and writes to the filesystem (--save,--export). - Sanitization: Absent.
Audit Metadata