matrixscan-ar-kmp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to retrieve a Scandit license key via an MCP server or user input and write it directly into the code as a literal value ("write it into the licence-key call in place of the placeholder"), rather than using environment variables.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to fetch documentation and dependency information from Sonatype Maven Central and Scandit documentation URLs, but does not monitor or ingest outsider-authored free text.