ClawHub

Baidu Qianfan Tools

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Baidu Qianfan API toolbox that sends user-provided prompts, queries, and image URLs to Baidu using the user's API key.

Install only if you intend to use Baidu Qianfan services. Use a dedicated API key with quota or billing limits, keep config.json and environment values private, and do not submit secrets, regulated data, private documents, or sensitive image URLs unless you are comfortable sending them to Baidu for processing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Low
Confidence
84% confidence
Finding
The documentation tells users to place `BAIDU_API_KEY` into environment variables or a local config file but never explicitly states that this key is a secret credential that must not be shared, committed, or exposed in logs. This can lead to accidental credential leakage through source control, screenshots, pasted configs, or shell history, which could allow unauthorized API use and billing abuse.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
This code transmits the raw user prompt to Baidu's remote chat API, but the file itself provides no user-facing disclosure, consent step, or privacy warning before exfiltrating potentially sensitive input. In a CLI/helper skill, users may reasonably paste secrets, internal data, or personal content, so silent third-party transmission creates a real confidentiality risk even if it is expected functionality.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
This code transmits user-supplied image URLs and optional product descriptions to Baidu's external API, which can expose user data to a third party without any disclosure or consent mechanism in this script. In a skill context, users may not realize their inputs are leaving the local environment, creating a privacy and data-handling risk rather than a memory-safety flaw.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal