Business Rule Engine

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.0

Overview

This appears to be a real business rule engine, but it evaluates rule text as Python code without clear warnings or containment.

Install only if all rule definitions and rule authors are trusted. Do not use this with customer-supplied, third-party, or remotely loaded rules until eval is replaced with a restricted parser or allowlisted evaluator and the trust boundary is documented.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• 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

Findings (3)

eval() call detected

High

• Category: Dangerous Code Execution

Content

# 安全求值 | Safe evaluation
        try:
            result = eval(expr, {"__builtins__": {}}, {})
            return bool(result)
        except:
            return False

• Confidence: 99% confidence
• Finding: result = eval(expr, {"__builtins__": {}}, {})

Intent-Code Divergence

High

• Confidence: 98% confidence
• Finding: This is the same core issue as the eval finding, compounded by misleading 'safe evaluation' comments that may cause reviewers or downstream users to trust dangerous behavior. The implementation performs raw string replacement and then executes the resulting Python expression, which is fragile and can be abused via crafted rule text or variable names/values.

Known Vulnerable Dependency: pytest — 1 advisory(ies): CVE-2025-71176 (pytest has vulnerable tmpdir handling)

Low

• Category: Supply Chain
• Confidence: 78% confidence
• Finding: pytest

VirusTotal

59/59 vendors flagged this skill as clean.