kicad-new-project
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes instructions and data from an external file (
DESIGN.md) through theview.pyscript to check design expectations. - Ingestion points: The agent is instructed to read
DESIGN.mdas part of the housekeeping and verification workflow. - Boundary markers: No specific boundary markers or 'ignore' instructions are provided to the agent when reading this file.
- Capability inventory: The skill possesses capabilities to execute shell commands via
$KPYand write project files (board, schematic, libraries). - Sanitization: There is no evidence of sanitization or validation of the content within
DESIGN.mdbefore it is processed by the agent. - [COMMAND_EXECUTION]: The skill uses a bundled Python interpreter (
$KPY) to execute various scripts (board.py,sch.py,check.py) with command-line arguments to create directories, generate PCB outlines, set design rules, and synchronize components.
Audit Metadata