ClawHub
Back to skill

Security audit

job-offer-comparator

Security checks for vulnerabilities and agentic risk

Overview

This is a local job-offer calculator whose file reading and Python execution are disclosed and limited to user-provided offer data.

Before installing, understand that the skill may run the bundled Python comparator and read offer JSON files you point it at. Avoid placing unrelated sensitive documents in the input file, and verify compensation assumptions because this is decision support, not tax or financial advice.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill documentation instructs the agent to read local files and execute shell commands (`python3 scripts/offer_compare.py ...`) but the skill declares no permissions. That mismatch is a real security issue because it can cause the platform or user to underestimate the skill's capabilities, increasing the chance of unintended file access or command execution in environments where such actions should be gated or explicitly approved.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/test_offer_compare.py:18