debug-bridge

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The runbook instructs agents to read and output sensitive values (cookies, localStorage tokens, network request/response bodies) and even shows typing a plaintext password example ("secret123"), which requires the LLM to handle and potentially emit secrets verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill implements an intentional remote-control/debug bridge that provides remote JavaScript execution, DOM/UI control, automatic capture/streaming of network requests/responses, console/errors, and access to localStorage/state — effectively a backdoor/telemetry exfiltration channel capable of stealing tokens and enabling remote code execution.