librarian
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Data is ingested from external PCB registries during searches and manufacturer datasheets referenced via URLs.
- Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions in the processed datasheets or registry packages.
- Capability inventory: The skill uses the
pcbCLI tool and various specialized artifact skills (kicad-symbol,kicad-footprint,zener-language,module-layout) to create and repair PCB components and modules. - Sanitization: There is no mention of sanitization, validation, or filtering of the content retrieved from external URLs or registries.
Audit Metadata