Back to skill

Security audit

run-options-forecast

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed options-analysis tool that uses an LSE API key to fetch market data and generate forecasts, trade ideas, dashboards, and optional logs, with no evidence of hidden exfiltration or account-changing behavior.

Install only if you are comfortable providing an LSE API key and letting the skill contact LSE market-data services. Treat generated options plays as research, not financial advice, verify prices independently, and consider pinning dependencies before use in a sensitive environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (11)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation describes executable components that use environment variables, write files, and access external network services, yet no permissions are declared. This creates a transparency and policy-enforcement gap: an agent or reviewer may authorize the skill based on incomplete capability disclosure, allowing outbound data access or filesystem side effects that were not explicitly consented to.

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding
The declared purpose is a narrowly scoped forecast/recommendation skill, but the documentation also exposes substantially broader behaviors including websocket streaming, backtesting, prediction logging/scoring, dashboard generation, and direct REST/WebSocket access. That mismatch is dangerous because operators may invoke or approve the skill expecting only local analysis, while hidden or underemphasized features expand the attack surface, data exposure, and side-effect profile.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This file generates and ranks concrete options trading strategies, including strikes, breakevens, probability of profit, and reward/risk, but the public outputs shown here do not include a clear user-facing disclaimer that the content is not investment advice and can result in substantial loss. In a retail-facing skill, presenting quantified trade recommendations without prominent risk warnings can encourage users to act on them as financial advice, especially given the authoritative formatting and ranking.

Unpinned Dependencies

Low
Category
Supply Chain
Content
scipy>=1.10
numpy>=1.24
python-dotenv>=1.0
plotly>=5.0
Confidence
93% confidence
Finding
scipy>=1.10

Unpinned Dependencies

Low
Category
Supply Chain
Content
scipy>=1.10
numpy>=1.24
python-dotenv>=1.0
plotly>=5.0
certifi>=2024.0
Confidence
93% confidence
Finding
numpy>=1.24

Unpinned Dependencies

Low
Category
Supply Chain
Content
scipy>=1.10
numpy>=1.24
python-dotenv>=1.0
plotly>=5.0
certifi>=2024.0
websocket-client>=1.6
Confidence
96% confidence
Finding
python-dotenv>=1.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
scipy>=1.10
numpy>=1.24
python-dotenv>=1.0
plotly>=5.0
certifi>=2024.0
websocket-client>=1.6
Confidence
92% confidence
Finding
plotly>=5.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
numpy>=1.24
python-dotenv>=1.0
plotly>=5.0
certifi>=2024.0
websocket-client>=1.6
Confidence
95% confidence
Finding
certifi>=2024.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
python-dotenv>=1.0
plotly>=5.0
certifi>=2024.0
websocket-client>=1.6
Confidence
92% confidence
Finding
websocket-client>=1.6

Known Vulnerable Dependency: python-dotenv==1.0 — 2 advisory(ies): CVE-2026-28684 (python-dotenv: Symlink following in set_key allows arbitrary file overwrite via ); CVE-2026-28684 (python-dotenv reads key-value pairs from a .env file and can set them as environ)

Medium
Category
Supply Chain
Confidence
80% confidence
Finding
python-dotenv==1.0

Known Vulnerable Dependency: certifi==2024.0 — 2 advisory(ies): CVE-2024-39689 (Certifi removes GLOBALTRUST root certificate); CVE-2024-39689 (Certifi is a curated collection of Root Certificates for validating the trustwor)

High
Category
Supply Chain
Confidence
63% confidence
Finding
certifi==2024.0

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.