qinghu-rednote-social
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external data from Xiaohongshu (Little Red Book), which includes user notes and comments. This data is untrusted and could potentially contain malicious instructions intended to influence the agent's behavior.\n
- Ingestion points: External data enters the agent's context through tools such as
rednote_note_comments,rednote_note_content, andrednote_search_notes, which fetch content and interaction data from the platform.\n - Boundary markers: The instructions do not specify the use of delimiters or provide the agent with guidance to ignore potential instructions embedded within the retrieved note content or comments.\n
- Capability inventory: The skill has the capability to perform network operations via API calls and export data using the
qinghu-excel-exportutility.\n - Sanitization: There are no protocols defined within the skill for sanitizing, escaping, or validating the external content before it is processed by the AI agent.
Audit Metadata