axe-ios-simulator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes a plaintext password ('secret123') embedded directly in an example command (axe type 'secret123'...), which would require the LLM to reproduce the secret verbatim in output, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes the AXe CLI’s runtime inputs for commands like axe type --stdin and axe type --file, meaning outsider-provided free text can be ingested via the --stdin/file-based text input path.