xiaohongshu-publish-hardened

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents a legitimate workflow for publishing posts on the official Xiaohongshu creator platform (creator.xiaohongshu.com).
  • [SAFE]: Includes comprehensive security guardrails that explicitly instruct the agent to refuse requests for automated credential entry, preventing potential harvesting of user passwords or verification codes.
  • [SAFE]: Implements instructions to block the transmission of platform-specific data (session tokens, account analytics) to external services, mitigating data exfiltration risks.
  • [SAFE]: Addresses indirect prompt injection risks by requiring the agent to only publish one post per explicit user request and forbidding batch operations, which prevents unauthorized bulk actions.
  • [SAFE]: All external references and documentation links point to the vendor's own infrastructure (faberlens.ai, github.com/faberlens) or the target service platform, following standard development and documentation practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:32 PM
Security Audit — agent-trust-hub — xiaohongshu-publish-hardened