huoshan-qifu-doc-knowledge-router

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only Feishu document router with one minor over-triggering risk, but no evidence of hidden writes, credential theft, persistence, or exfiltration.

Install only if you expect the agent to use your Feishu account to read Huoshan/Qifu knowledge documents. Be aware it may request Wiki and Docx read-only scopes, and the publisher should ideally narrow the generic source-grounded-answer trigger to avoid accidental activation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description contains broad trigger phrases such as generic knowledge retrieval, document recommendation, and source-grounded answers, which can cause the router to activate for common enterprise queries beyond a narrowly scoped domain. This increases the chance of unintended tool use and unnecessary access to internal document indexes, especially when users did not explicitly request this skill.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal