matrixscan-pick-ios

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to retrieve a license key via MCP and paste it directly into the code rather than using environment variables or a secure configuration.

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 LLM to fetch GitHub repository URLs when requested by the user, but does not monitor or automatically consume outsider-authored free text without user selection.