kicad-part-selection
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to search for part information and read datasheets from external, third-party URLs. This introduces a surface for indirect prompt injection, as an attacker could theoretically place malicious instructions within a datasheet or product description that the agent is directed to process.\n
- Ingestion points: Third-party distributor websites (jlcpcb.com, lcsc.com, DigiKey, Mouser) and external PDF URLs for datasheets.\n
- Boundary markers: Absent. The skill does not provide instructions to the agent to treat external data as untrusted or to ignore instructions embedded within retrieved content.\n
- Capability inventory: The agent is empowered to modify local project files using tools such as
kicad-schematicandkicad-board-edit(invokingboard.py sync).\n - Sanitization: Absent. There are no guidelines provided for validating or sanitizing the information gathered from external sources before it is utilized in the design or recorded in the schematic.
Audit Metadata