小红书认证管理技能。检查登录状态、登录(二维码或手机号)、退出登录。 当用户要求登录小红书、检查登录状态、退出登录时触发。
69
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The skill explicitly instructs the agent to ask for and then embed user phone numbers and one-time SMS verification codes verbatim into CLI commands (e.g., send-code --phone and verify-code --code), forcing the LLM to handle secret values directly and risking exfiltration.
b043748
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.