Back to skill

Security audit

Requirement Guide

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward requirements-questionnaire helper that only stores user-provided sessions or documents when explicitly asked.

Before installing, treat saved requirement JSON as project data: store it in an appropriate workspace, avoid reusing paths you do not want overwritten, and do not include secrets or confidential details unless that location is acceptable.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_read' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_write' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The markdown explicitly advertises persistence via save/load of sessions and documents, which affects user data on the filesystem. While the behavior is documented functionally, there is no user-facing warning or caution about local file creation/overwrite implications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill persists potentially sensitive requirement data and generated documents to disk without any built-in disclosure, confirmation, or visibility to the user at the API level. Requirement sessions may contain business context, security requirements, interfaces, and constraints, so silent persistence can create privacy and data-handling risks if users do not expect local storage.

Content

No source excerpt is available for this finding.