tencent-cloud-cos

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to request users' SecretId/SecretKey and shows commands that embed those secrets (export lines and an alternative --secret-id/--secret-key CLI form) and also persists them to config files, which requires the LLM to handle or generate output containing secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). 在运行时通过 Clawdbot/用户自然语言触发包装器调用后，外部用户可提供任意 text/key 等参数进入 scripts/cos_wrapper.py（如 search_by_text(text)），这些自由文本会被直接传给 cos-mcp 的工具参数用于智能搜索。