The Agent Skills Directory

[SAFE]: The skill instructions are focused on hardware engineering documentation and test planning. No network access, credential handling, or suspicious code execution patterns were identified.
[COMMAND_EXECUTION]: The skill instructs the agent to run a local script view.py (via the kicad-view tool) to calculate resistance values from a KiCad netlist. This is a legitimate use of project-specific tooling as intended for hardware design verification.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to ingest data from KiCad schematic files (board.kicad_sch) and design notes to generate the test plan.
Ingestion points: Untrusted hardware design data from .kicad_sch files and project documentation.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the schematic data processing.
Capability inventory: The skill performs filesystem writes to TEST_PLAN.md based on the ingested data.
Sanitization: No explicit sanitization or validation of the schematic content is performed before generating the report. However, the structured, domain-specific nature of KiCad schematic data poses a negligible risk for indirect prompt injection compared to natural language inputs.

kicad-bringup