matrixscan-count-kmp
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The static detector flagged a potential concealment pattern based on instructions telling the agent not to advise users to check the documentation themselves. However, the skill explicitly requires the agent to provide direct links to the official documentation when answering, ensuring transparency and providing the user with direct access to sources.
- [EXTERNAL_DOWNLOADS]: The skill references official Scandit Maven artifacts (
com.scandit.datacapture.kmp) and the official Swift Package Manager repository (Scandit/datacapture-kmp-spm). These are verified resources belonging to the vendor 'scandit'. - [INDIRECT_PROMPT_INJECTION]: The skill documents the handling of barcode data (
barcode.data). - Ingestion points: Barcode data is processed in
onScancallbacks described inreferences/integration.md. - Boundary markers: None explicitly defined for the data content.
- Capability inventory: The skill provides documentation only and does not contain scripts with file-system writes, network exfiltration, or command execution capabilities.
- Sanitization: Not applicable as the skill does not perform data processing itself, but rather documents how a user's app should handle the SDK.
Audit Metadata