xhs-search
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a legitimate search workflow for a social media platform. It lacks any patterns associated with obfuscation, privilege escalation, or persistence.
- [PROMPT_INJECTION]: Potential for indirect prompt injection as the skill processes search results from a public platform. Evidence Chain: 1. Ingestion points: Xiaohongshu search results via the search_feeds tool. 2. Boundary markers: Absent. 3. Capability inventory: Information retrieval and display only. 4. Sanitization: Absent. The risk is minimized by the read-only nature of the skill.
Audit Metadata