skills/l3wi/claude-eda/eda-drc/Gen Agent Trust Hub

eda-drc

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted design files which serves as a potential vector for indirect prompt injection. Evidence Chain: 1. Ingestion points: hardware/*.kicad_sch, hardware/*.kicad_pcb, and docs/design-constraints.json. 2. Boundary markers: Absent; there are no explicit delimiters or instructions for the agent to ignore embedded text in design files. 3. Capability inventory: MCP tools for KiCad and JLC, and file system Write access for reporting. 4. Sanitization: Absent; no validation or filtering of design file content or metadata is specified.
  • [Data Exposure & Exfiltration] (SAFE): Network activity through WebSearch and mcp__jlc__* tools is strictly limited to the skill's primary purpose of component validation and does not involve access to or transmission of sensitive user credentials or system files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM