claude-computer-use-advanced

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed API keys directly in code (e.g., client = anthropic.Anthropic(api_key="your-api-key")) and describes typing/entering credentials into fields, which encourages the agent to receive and emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill enables the agent to capture and analyze arbitrary on-screen content (including web pages and web forms) via screenshots and OCR—see the Quick Start "Fill out the contact form" example and the "Screen Analysis & Data Extraction" section—so it can ingest untrusted public third‑party content (websites/user-generated pages) that could carry indirect prompt injection.