Back to skill

Security audit

questionnaire-quality-checker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused questionnaire-data checker that reads user-supplied CSV and JSON files and optionally writes a local report, with no hidden network, persistence, or credential behavior found.

Install this if you are comfortable letting the agent run the included local Python checker on questionnaire CSV files and a JSON config you choose. Keep inputs and output paths scoped to the intended project directory, and review flagged cases before making data-exclusion decisions.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill instructs the agent to run a local Python script against user-supplied CSV and JSON files and optionally write a report, which implies file read/write and code-execution capabilities, but the manifest does not declare any tool scope such as permissions or allowed-tools. This creates a least-privilege and governance gap: an agent platform may expose broader filesystem or execution access than intended, making accidental overreach or misuse of local files more likely.

Content

No source excerpt is available for this finding.