Skills
Navigate
skills/roccoagain/kicad-agent-skills/kicad-layout-review/Gen Agent Trust Hub

kicad-layout-review

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external project data, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: The agent reads board files (board.kicad_pcb), design notes (DESIGN.md, CLAUDE.md, AGENTS.md), and TEST_PLAN.md.
  • Boundary markers: The skill does not provide delimiters or specific instructions to isolate the data content from the agent's instructions.
  • Capability inventory: The skill executes local Python scripts (board.py, view.py) and generates review reports.
  • Sanitization: Input data from board files and documentation is not sanitized or validated before processing.
  • [COMMAND_EXECUTION]: The skill invokes local utility scripts to extract information from PCB layout files.
  • Evidence: Uses board.py with subcommands like pads, tracks, and nets, and view.py for visual inspection of the board.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 09:06 AM