browserwing-admin

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill contains curl examples and API fields that embed API keys, bearer tokens, and cookie values directly in requests (e.g., "api_key": "sk-xxx", Authorization: Bearer , cookie "value": "abc123"), which requires the LLM/agent to handle and output secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The outsider-supplied free text task_desc in POST /api/v1/ai-explore/start is provided to BrowserWing’s AI exploration workflow, which will then ingest and act on that text at runtime.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs running sudo commands that modify apt keys and /etc/apt/sources.list.d (and suggests using --no-sandbox), which requests privilege escalation and bypasses sandboxing and thus can change the host system state.