ClawAudit verdict

xiaohongshu-mcp-node

xiaohongshu-mcp-node-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

MCP server integration for Xiaohongshu platform operations; all network calls go to xiaohongshu.com via a documented MCP server with user-provided credentials stored locally.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

15
security
90
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

references/quick-start.md · code · curl -fsSL https://raw.githubusercontent.com/sipingme/xiaohongshu-mcp-node-skill

Pattern match critical

Pipe to bash — executes piped content as shell commands

references/quick-start.md · code · | bash

Pattern match high

Accesses shell history/config

references/faq.md · code · ~/.zshrc

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

network_inpackage_installdata_encoding

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API