solidcraft
Warn
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The
SKILL.mdfile contains explicit instructions directing the agent to execute shell commands viaosascriptto bring the application window to the foreground on macOS. - [COMMAND_EXECUTION]: The provided script
scripts/sc.pyusessubprocess.run()within itswakecommand to executeosascriptcommands for system-level window management. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted CAD data and JSON scripts, which serves as a surface for indirect prompt injection attacks.
- Ingestion points: Untrusted content enters the agent's context through file loading commands such as
doc.open,file.insert_step, andsolidcraft-cli run. - Boundary markers: Absent; the skill instructions do not implement delimiters or ignore-instructions warnings for processed external files.
- Capability inventory: The skill can perform filesystem writes (
file.export), execute CAD engine commands, and invoke system-level shell commands (osascript). - Sanitization: Beyond basic JSON schema validation for parameters, the skill does not sanitize the semantic content of processed files.
- [EXTERNAL_DOWNLOADS]: The skill documentation references and encourages fetching additional modeling resources and functional skills from the
tangency-labsGitHub organization.
Audit Metadata