congress-stock-tracker

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:32 PM UTC
• Version:
  1.0.1

Overview

This skill fetches public congressional trade data and creates analysis reports, with no hidden persistence, credential use, or destructive behavior found.

Install only if you are comfortable with the agent fetching public data from Capitol Trades and, when you choose an output path, writing report files locally. Treat policy-catalyst and anomaly interpretations as research leads, not investment advice, and verify important financial conclusions independently.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 86% confidence
• Finding: The skill instructs the agent to run a Python script that fetches data from external sources and can write output files, but the skill metadata does not declare corresponding network or file-write permissions. This creates a capability/permission mismatch that weakens security review and runtime policy enforcement, because operators and sandboxes may underestimate what the skill can do.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 84% confidence
• Finding: The skill claims deeper analytical behavior—committee correlation, legislative/regulatory event analysis, and policy-catalyst inference—but the described implementation only performs simple rules over trade fields. This mismatch is dangerous because users may trust fabricated or overstated conclusions, leading to deceptive automation and unsafe decisions based on analysis the tool did not actually perform.

VirusTotal

63/63 vendors flagged this skill as clean.