Zhihu Keyword Search API

Security checks across malware telemetry and agentic risk

Overview

This skill is narrowly built for Zhihu search, but it handles the required API token in ways that can leak it through URLs or local command arguments.

Install only if you are comfortable with your JustOneAPI token being passed as a command argument and sent in the request URL. Prefer a revised version that reads the token directly from the environment and sends it in an authorization header if the service supports that. Rotate the token if you suspect it has appeared in logs, shell history, monitoring, or error reports.

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 (1)

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill defines the API credential as a required query parameter (`token`) and later appends all query parameters to the URL. Query-string secrets are routinely exposed in logs, browser/history artifacts, reverse proxies, monitoring systems, and error reports, so the token can be disclosed even when TLS is used. In this skill's context, the token is the primary authenticator for a third-party API, making leakage directly useful for unauthorized API use.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal