ClawHub

Douban Movie Comments API

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it calls one JustOneAPI Douban movie comments endpoint using a user-provided API token.

Install only if you trust JustOneAPI with this API token. Use a scoped or easily rotated token where possible, and be aware that this helper places the token in the request URL, which can be captured by server logs, proxies, or debugging output.

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
96% confidence
Finding
The skill defines the API access token as a query parameter and appends it to the request URL. Query-string credentials are commonly exposed through logs, browser/history tooling, proxy telemetry, monitoring systems, and error messages, so the token may be disclosed beyond the intended recipient. In this skill context, the risk is real because the script also surfaces structured error details and constructs a plain GET URL, making accidental token propagation more likely.

Missing User Warnings

Medium
Confidence
76% confidence
Finding
This skill requires a credential and transmits it to a third-party network API, but the manifest provides no user-facing warning about credential handling, transmission, or data-sharing implications. In an agent setting, that can lead users to provide sensitive tokens without understanding where they are sent or how they are used, increasing the risk of inadvertent credential exposure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal