xiaohongshu-mcp
Fail
Audited by Snyk on Mar 10, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill shows and requires passing an xsec_token/feed_id (a session/security token) directly as a command-line argument and instructs using tokens returned by search in subsequent commands, which forces the agent to handle and output secret values verbatim.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). SKILL.md shows the skill uses the bundled client to run "search" and "detail" against Xiaohongshu (public user-generated notes and comments), so the agent fetches and analyzes untrusted third‑party content (notes/comments) that can influence its decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires downloading and running binaries from the project's GitHub releases (https://github.com/xpzouying/xiaohongshu-mcp/releases), which are remote executables fetched and executed at runtime and therefore constitute an external runtime dependency that runs remote code.
Audit Metadata