ClawHub

快手评论分析

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a purpose-aligned Kuaishou analysis helper, with some transparency and invocation-scope caveats but no evidence of malware, deception, destructive action, or credential theft.

Install only if you trust the API provider and are comfortable sending Kuaishou links or related metadata to that service. Prefer explicit invocation for sensitive conversations, and store any API key locally rather than pasting it into chat.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill declares required environment variables and explicitly performs outbound API calls and polling, but no permissions model is documented to inform users that the skill can access secrets and the network. This creates a transparency and least-privilege problem: a host or reviewer cannot readily constrain or audit what external destinations may receive data, including user-supplied links and API-backed metadata.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill enables implicit invocation without any trigger constraints, which allows the assistant to activate it automatically in a broad range of conversations. Because this skill processes user-provided 快手 content links and performs sentiment/profile/public-opinion analysis, unintended invocation could expose user inputs to the skill unnecessarily, create surprise data handling, or cause the model to route sensitive conversations into an external workflow without clear user intent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal