ClawHub

clawto-market-intel

Security checks across malware telemetry and agentic risk

Overview

This skill fetches public market data and news for market summaries, with no evidence of credential theft, persistence, destructive behavior, or hidden data exfiltration.

Install only if you want a market-data summarizer that contacts public finance, news, and crypto data services. Treat its strategy-style output as informational, not financial advice, and be aware broad finance phrases may trigger it in ordinary market discussions.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill advertises shell scripts and multiple external data sources, which implies network and shell execution capabilities, yet no permissions are declared in the manifest. This creates a transparency and governance gap: users or hosting platforms cannot accurately assess what the skill is allowed to do, and any later script changes could expand outbound access or command behavior without an explicit permission boundary.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger set is broad enough to match common finance-related conversation such as '行情', '指数', or '走势', which can cause the skill to activate when the user did not explicitly request it. In an agent environment, unintended invocation can lead to prompt hijacking opportunities, irrelevant data retrieval, or disclosure of contextual information to external data-fetching logic.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger list contains very broad financial terms such as '行情', '指数', '大盘', '股价', and '要闻', which can match ordinary financial conversation far beyond the intended use case. Over-broad activation increases the chance the skill runs in unintended contexts, causing unnecessary network access, data retrieval, or tool invocation when the user did not explicitly request this skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal