csdn-article-publish

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to execute a Node.js script (scripts/csdn_article.js) to perform article management tasks.
  • [DATA_EXFILTRATION]: The script reads authentication credentials (session cookies and API signatures) from the local csdn_config.json file and transmits them to the official CSDN API endpoint (bizapi.csdn.net). This is a well-known service, and the operation is necessary for the skill to authenticate with the user's account.
  • [SAFE]: The skill includes a local, bundled version of the 'marked' library (scripts/marked.umd.js) to convert Markdown content to HTML before publication. This processing is performed entirely within the local environment.
  • [SAFE]: The script implements built-in configuration validation to ensure that sensitive fields are correctly populated and not left as placeholder values from the example template.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 01:01 PM