akcli-jlcpcb-capabilities

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process user-supplied KiCad design files (.kicad_pcb, .kicad_sch) and fabrication profiles (.toml) through subprocess tools like kicad-cli and akcli. This ingestion of untrusted CAD data and configuration files creates a surface for indirect prompt injection if the files contain malicious strings (such as footprint names, silkscreen text, or netlist attributes) intended to influence the agent's interpretation of tool outputs.
  • Ingestion points: board.kicad_pcb, board.kicad_sch, and order.toml files mentioned in the manufacturing handoff section of SKILL.md and cost-and-fab-profile.md.
  • Boundary markers: The skill does not define specific delimiters or instructional guardrails for the data extracted from the design or profile files.
  • Capability inventory: The skill utilizes subprocess calls to kicad-cli and akcli for design rule checking, fabrication audits, and artifact generation.
  • Sanitization: There is no explicit description of filtering, validation, or sanitization of component metadata or other user-controlled strings within the PCB files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 02:47 AM