kicad-design-review
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including schematic files, netlists, and component datasheets. This creates a surface for indirect prompt injection where an attacker could embed malicious instructions within these files (e.g., in schematic comments or datasheet metadata) to manipulate the agent's analysis or output.
- Ingestion points: Processes schematics and netlists via the
kicad-viewtool and reads external datasheet content. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore or distinguish embedded natural language instructions within the processed data.
- Capability inventory: The skill utilizes simulation tools (
kicad-simulate) and generates reports that could potentially be used to exfiltrate information or mislead the user if the agent's logic is subverted. - Sanitization: There is no evidence of sanitization or validation of the content extracted from external datasheets or KiCad files.
Audit Metadata