write-xiaohongshu

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core data-processing workflows.
  • Ingestion points: The agent is instructed to fetch and analyze content and comments from Xiaohongshu posts using the get_specified_post tool, as well as background information from the web via the Firecrawl MCP.
  • Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' commands to prevent the agent from obeying instructions that may be embedded within the ingested external data.
  • Capability inventory: The agent has the capability to publish content directly to a user's Xiaohongshu account using the Xiaohongshu MCP tool.
  • Sanitization: The skill does not provide mechanisms for sanitizing or validating external content before it is used to generate and publish social media notes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:14 PM