ClawHub
Back to skill

Security audit

Zhihu Column Article Details API

Security checks across malware telemetry and agentic risk

Overview

This is a focused Zhihu article-detail lookup through JustOneAPI, with the main caution being careful handling of the API token.

Install only if you are comfortable sending a JustOneAPI token and the requested Zhihu article id to api.justoneapi.com. Use a restricted, rotatable token where possible, avoid running it on shared machines, and do not paste token values into chat or logs.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The manifest requires a token to be sent as a query parameter to an external API, but it provides no user-facing disclosure about credential handling, third-party transmission, or logging exposure. Query-string tokens are particularly risky because they may be captured in logs, proxies, browser histories, or monitoring systems, increasing the chance of credential leakage.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill requires a credential-like `token` query parameter but does not warn that sensitive authentication material must be supplied and handled securely. In an agent context, this can lead to users or upstream systems providing secrets without understanding exposure risks, and query-string tokens are especially prone to logging, leakage via telemetry, and accidental disclosure.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.md:41