Security audit
Security checks for vulnerabilities and agentic risk
The skill is a disclosed social-media automation tool, but it asks for account credentials and can publish scheduled public posts without strong safeguards.
Review this carefully before installing. Only use it with accounts where automated public posting is acceptable, protect the configured API keys/tokens/cookies, avoid committing the config file, and do not enable the cron schedule unless you are comfortable with queued posts running without a new confirmation.
This markdown file tells users to add platform credentials to a configuration file, but it does not include any caution about storing secrets securely, limiting access, or avoiding accidental exposure. Because credentials affect user privacy and account security, the skill description should explicitly warn users about this sensitive setup step.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
crontab -e
# 添加 crontab-example.txt 中的内容
The skill describes capabilities that imply reading/writing local configuration and using network access to publish content, schedule tasks, and interact with platform APIs, but it does not declare any explicit tool scope or permissions boundary. This creates a transparency and least-privilege problem: users and enforcement systems cannot easily verify what resources the skill is allowed to access, increasing the risk of overbroad file or network operations on the user's behalf.
The top-level description is written as a Chinese-only product description for a multi-platform social posting assistant, with no indication that users may choose their preferred language. This can violate language/locale policy because the skill appears to impose a specific language without opt-in or justification.
The workflow states that the skill can automatically publish scheduled posts and monitor comments with auto-replies, but the user-facing description does not clearly warn that actions may occur later and without a fresh confirmation at execution time. In a social-media automation context, this can lead to unauthorized, mistimed, or reputation-damaging posts and replies if content is queued, misconfigured, or triggered after circumstances change.
The configuration instructs users to place API keys, access tokens, and a platform cookie into a local JSON file but does not warn about the sensitivity of these secrets or safe storage practices. Exposure of these credentials could allow takeover of connected social accounts, unauthorized posting, scraping, or impersonation across multiple platforms.
The package description is written as a Chinese-language social media automation assistant with no indication that users can choose another language or locale. This can violate language/locale policy because the skill appears scoped to a specific language experience without documented opt-in or justification in the file.
The scheduled runner automatically posts outbound content and permanently updates task state without any execution-time confirmation, dry-run, or approval gate. In a social-media automation skill, this can cause unintended or unauthorized posts if tasks are added mistakenly, the task file is tampered with, or the script is invoked by another process, leading to reputational damage and account misuse.
All user-facing instructions in this file are presented in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience for compliance or regional reasons. This can violate language/locale policy when a specific language is imposed without opt-in or justification.
The file’s natural-language comments are written only in Chinese (e.g. '每天上午 9 点执行发布任务'), which imposes a specific language on users without any opt-in or explanation. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific.
User-facing strings such as the file description, docstrings, and CLI usage text are written exclusively in Chinese. Under the policy, forcing a specific language without offering the user a choice or documenting a justified locale constraint is a natural-language policy issue.
No suspicious patterns detected.