kicad-schematic-review
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing local command-line tools and scripts to perform its analysis. Evidence: Mentions of 'view.py', 'kicad-simulate', and 'kicad-view' as tools for the agent to use.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data sources, representing a potential attack surface for indirect prompt injection. 1. Ingestion points: Reads KiCad schematic files ('.kicad_sch'), netlists, and external component datasheets. 2. Boundary markers: The instructions do not define specific markers to isolate untrusted data from instructions. 3. Capability inventory: The agent has access to shell command execution through 'view.py' and 'kicad-simulate'. 4. Sanitization: No explicit validation or sanitization of the ingested files is mentioned.
Audit Metadata