kicad-schematic
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection through its requirement to download and process external PDF datasheets and internet search results.
- Ingestion points: Untrusted data enters the agent's context through external PDF files and search engine results as described in the 'How to do research' section (SKILL.md).
- Boundary markers: The instructions do not provide delimiters or specific 'ignore embedded instructions' warnings for the processed data.
- Capability inventory: The skill uses file write operations (
SaveDocument) and network capabilities (internet search and downloads). - Sanitization: No sanitization or validation of the content extracted from external PDFs or websites is mentioned.
- [INDIRECT_PROMPT_INJECTION]: The skill explicitly instructs the agent to 'find ways around' bot protection when downloading datasheets. This directive encourages the agent to bypass security controls on third-party websites, which could lead to unintended behaviors or access to malicious content designed to exploit the agent's parsing capabilities.
Audit Metadata