Security audit

yanlin-macro-data

Security checks across malware telemetry and agentic risk

Overview

This skill is a small macro-market data helper with disclosed public network reads, but its documentation has data-quality inconsistencies users should notice.

Install only if you are comfortable with the skill making public requests to Sina Finance and using mostly built-in teaching snapshots. Do not rely on its numbers for investment decisions, and treat the northbound-flow example as unsupported unless the publisher fixes the documentation and implementation mismatch.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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: 90% confidence
Finding: The skill advertises network-backed data collection but does not declare corresponding permissions, creating a transparency and policy-enforcement gap. Undeclared network capability can cause operators to approve or run the skill without understanding that it may make external requests and exfiltrate prompts, metadata, or usage patterns to third parties.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The documented purpose does not accurately match the described behavior: it omits real network retrieval of commodity and US stock quotes, claims northbound flow coverage that is not implemented, and relies heavily on hardcoded snapshot data rather than true collection. This mismatch is dangerous because users and security reviewers may make trust decisions based on the stated scope while the skill behaves differently, enabling unauthorized external access and misleading downstream financial use.

Intent-Code Divergence

Medium

Confidence: 88% confidence
Finding: The documentation says the skill does not include northbound capital flow data, but the sample output contains a north_flow field, which is internally inconsistent. Such contradictions are risky because consumers may build logic or make decisions assuming the field is supported and trustworthy, when it may be fabricated, stale, or absent at runtime.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.