Security audit

独孤九剑V2

Security checks across malware telemetry and agentic risk

Overview

This stock-analysis skill is coherent and purpose-aligned, but users should understand that it contacts public market-data providers and may create local chart files.

Install only if you are comfortable with the skill contacting external Chinese market-data/news providers for requested tickers and saving generated chart PNGs locally. Prefer a virtual environment with pinned dependencies, and treat the trading output as analysis support rather than financial advice.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection

Findings (11)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 86% confidence
Finding: The skill clearly instructs the agent to fetch live stock, capital-flow, and potentially news data from external services, yet no permissions are declared. This creates an undeclared network capability that can surprise hosts, bypass expected consent boundaries, and expose user queries or usage metadata to third-party endpoints.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 81% confidence
Finding: The advertised purpose is stock analysis, but the skill also exposes standalone framework-retrieval and chart-generation/file-writing capabilities. This widens the attack surface beyond the stated function, making it easier for users or other agents to invoke unintended behaviors and increasing the risk of unauthorized local file creation or capability misuse.

Context-Inappropriate Capability

Medium

Confidence: 92% confidence
Finding: The code explicitly implements anti-blocking measures such as randomized delays, User-Agent rotation, retries, and '防御层' logic to sustain access to third-party data sources. In a skill context, this crosses from ordinary API consumption into stealthy scraping behavior that can evade provider controls and may violate service terms, increasing legal, operational, and abuse risk.

Missing User Warnings

Low

Confidence: 78% confidence
Finding: The description omits a warning that the skill will fetch stock and possibly news data from external providers. Users may assume analysis is local, causing uninformed disclosure of requested tickers, timing, and related prompts to third parties, which is a transparency and privacy issue.

Unpinned Dependencies

Low

Category: Supply Chain
Content: akshare>=1.12.0 pandas>=1.5.0 numpy>=1.24.0 mplfinance>=0.12.10
Confidence: 96% confidence
Finding: akshare>=1.12.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: akshare>=1.12.0 pandas>=1.5.0 numpy>=1.24.0 mplfinance>=0.12.10 matplotlib>=3.7.0
Confidence: 96% confidence
Finding: pandas>=1.5.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: akshare>=1.12.0 pandas>=1.5.0 numpy>=1.24.0 mplfinance>=0.12.10 matplotlib>=3.7.0 requests>=2.28.0
Confidence: 96% confidence
Finding: numpy>=1.24.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: akshare>=1.12.0 pandas>=1.5.0 numpy>=1.24.0 mplfinance>=0.12.10 matplotlib>=3.7.0 requests>=2.28.0
Confidence: 95% confidence
Finding: mplfinance>=0.12.10

Unpinned Dependencies

Low

Category: Supply Chain
Content: pandas>=1.5.0 numpy>=1.24.0 mplfinance>=0.12.10 matplotlib>=3.7.0 requests>=2.28.0
Confidence: 95% confidence
Finding: matplotlib>=3.7.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: numpy>=1.24.0 mplfinance>=0.12.10 matplotlib>=3.7.0 requests>=2.28.0
Confidence: 93% confidence
Finding: requests>=2.28.0

Known Vulnerable Dependency: requests==2.28.0 — 8 advisory(ies): CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi); CVE-2026-25645 (Requests has Insecure Temp File Reuse in its extract_zipped_paths() utility func) +5 more

High

Category: Supply Chain
Confidence: 90% confidence
Finding: requests==2.28.0

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.