skills/alivirgo/major-ai-skills/kicad/Gen Agent Trust Hub

kicad

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official KiCad Docker images (kicad/kicad:8.0) and the community-standard InteractiveHtmlBom plugin. These are well-known resources within the electronics engineering ecosystem and are used for their intended purposes.
  • [COMMAND_EXECUTION]: The Python scripts use subprocess.run to call external KiCad utilities like generate_interactive_bom.py. This is a standard method for integrating KiCad's modular tools into an automated workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection as it ingests external S-expression files (.kicad_pcb, .kicad_sch).
  • Ingestion points: External KiCad PCB and schematic files are loaded via pcbnew.LoadBoard() and parsed by the provided automation scripts.
  • Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore embedded comments within the ECAD files.
  • Capability inventory: The skill has the capability to write to the file system (board.Save()) and execute shell commands via subprocess.run.
  • Sanitization: There is no explicit sanitization of text fields within the S-expression files (like component values or notes) before they are processed, though the risk is minimized by the highly structured nature of the EDA data format.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:55 AM