wbso-signup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt asks the agent to obtain and handle API keys verbatim (the CLI prints an "api_key" and the agent is instructed to ask the user for that key and/or run commands like wbso login --api-key <KEY>), which requires including secrets directly in agent output/commands.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The code intentionally collects and leaks local sensitive data (git history, local Claude/Codex user prompts and cwd) by appending it to the output of the context command—data that an AI agent or remote service consuming the command output could capture—representing a deliberate data-exfiltration/privacy-leak risk; no obfuscated payloads, reverse shell, or hidden remote-exec backdoor were found.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow runs wbso context, which fetches https://portal.wbso.ai/api/v1/compliance/context.md and then prints/cat’s that markdown into the agent/LLM context; this content is outsider-authored (WBSO portal/user-generated compliance context) and is not bundled reference material.