The Agent Skills Directory

[SAFE]: The skill provides legitimate documentation and integration instructions for the Scandit Parser KMP SDK. It correctly identifies the specific requirements and API differences for the Kotlin Multiplatform environment.
[CREDENTIALS_UNSAFE]: The skill includes security-conscious instructions for handling license keys. It explicitly mandates that the agent only show masked previews in chat and prohibits the agent from searching the local environment or project files for credentials, which aligns with security best practices for secret management.
[EXTERNAL_DOWNLOADS]: The skill references official and well-known sources for dependencies, including Sonatype Central for Maven artifacts and the vendor's official repository for Swift Packages. These references are documented neutrally as part of the standard project setup process.
[INDIRECT_PROMPT_INJECTION]: While the skill describes processing external data (such as barcode and RFID strings), it acts as a structured data transformation component. It does not possess dangerous capabilities like arbitrary command execution, file-system writes, or unauthorized network exfiltration, resulting in a safe posture regarding data ingestion.

parser-kmp