id-capture-kmp
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill employs instructional language to prioritize provided technical references over the agent's training data. This is used to ensure code correctness for a new SDK and does not constitute an attempt to bypass safety protocols.
- [DATA_EXPOSURE]: The instructions include defensive measures for license key handling, such as masking previews in chat and prohibiting the agent from searching the local filesystem for credentials.
- [EXTERNAL_DOWNLOADS]: External references are limited to official Scandit documentation and standard package registries like Maven Central, which are considered safe and authoritative sources.
Audit Metadata