Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent Chinese social-platform formatting and simulated publishing helper, but its simulated publish path unnecessarily checks for configured platform credentials.
Install only if you want a Chinese social-platform workflow. Treat real publishing as not implemented despite the credential documentation, and be aware that the simulated publish command may still read configured platform credentials from environment variables or local config files before only printing simulated output.
The README explicitly frames the skill as supporting only '4 大中文平台' and the usage and platform support are entirely tied to Chinese platforms, without offering users a language or locale choice. This can violate a language/locale policy when a skill constrains output or workflow to a specific locale without explicit opt-in or justification.
The module docstring and subsequent CLI/help/output text are written in Chinese and present the skill as supporting Chinese social platforms, but there is no indication that language is user-selectable or explicitly limited by design. This can violate language/locale policy because the skill effectively forces a specific language without opt-in.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
def publish_to_xiaohongshu(title, content, images):
"""小红书发布（需要真实API）"""
# TODO: 实现小红书开放平台 API
# 接口: https://api.xiaohongshu.com/api/sns/v1/note/publish
simulate_publish("xiaohongshu", title, content, images)
def publish_to_zhihu(title, content, images):
The code comments and user-facing messaging state that publishing is currently simulated and that real APIs are not enabled, yet the non-format path still loads credentials from environment variables/config files and aborts if none are present. That contradicts the apparent intent of a simulation-only tool, because simulation should not depend on real secrets being configured.
The manifest description is entirely in Chinese and frames the skill specifically around Chinese publishing platforms, with no indication that users can choose another language or locale. This can violate language/locale policy expectations when a skill is presented to a broader audience without explicit opt-in or justification.
No suspicious patterns detected.