xiaohongshu-keyword-collector

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs legitimate browser automation tasks targeting Xiaohongshu (a well-known service) for keyword discovery. No obfuscation, persistence mechanisms, or unauthorized privilege escalations were detected.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from an external platform without validation (Category 8).
  • Ingestion points: Search suggestions scraped from the Xiaohongshu Explore page UI as described in SKILL.md.
  • Boundary markers: None identified; the skill does not use delimiters or instructions to ignore potential commands embedded in the scraped text.
  • Capability inventory: The skill utilizes the browser tool to navigate to URLs, interact with input fields, and read DOM content.
  • Sanitization: No sanitization or filtering is applied to the keywords collected from the website before they are returned to the user or processed further.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 04:17 AM
Security Audit — agent-trust-hub — xiaohongshu-keyword-collector