xiaohongshu-skill Audit report.

Warnings

• Permission surface may require sandboxing
• The SKILL.md is extremely long and complex, with many internal references and contracts. This may make it difficult for agents to parse and follow consistently, especially in a single context window.
• The skill relies heavily on host-native image generation (Image2) and MCP tools; if those are unavailable, the fallback logic is complex and may lead to confusion about when local SVG/HTML is allowed.
• The skill includes many rules about user confirmation and auto-permission states, which could be error-prone if the agent misinterprets the original user intent.
• Quality score needs review
• Permission surface needs review: shell or command execution, filesystem or document access
• Stars/forks activity: 169 stars, 49 forks; issue activity unavailable in current metadata
• Permission surface: shell or command execution, filesystem or document access

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.