News - 热门新闻

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal news lookup skill that uses a JisuAPI key, with only mild caution about sending news queries to an external provider.

Install this if you want news aggregation through JisuAPI and are comfortable configuring a JISU_API_KEY. Treat anything you ask it to search as data sent to the third-party API, and use specific news requests rather than private or unrelated prompts.

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: 84% confidence
Finding: The skill metadata declares required binaries and environment variables, and the documented usage clearly invokes an external API using an API key, but there is no explicit permission model describing network/env access. This creates a transparency and governance gap: agents or reviewers may underestimate that the skill can transmit user queries and secrets-derived authentication to a third party.

Vague Triggers

Medium

Confidence: 81% confidence
Finding: The trigger description includes the broad phrase '或类似新闻聚合问题', which leaves activation boundaries vague. Overbroad matching can cause the agent to invoke this networked skill for loosely related prompts, unnecessarily sending user queries to an external service and increasing the chance of unintended data disclosure or tool misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal