Back to skill

Security audit

Graphql Client

Security checks for vulnerabilities and agentic risk

Overview

This skill only prints local reference text and shows no evidence of credential access, network activity, persistence, or hidden behavior.

Safe to install from a security perspective, but treat it as shallow generic notes rather than authoritative GraphQL client documentation. Use the listed debugging command instead of the cheatsheet's troubleshooting label.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/script.sh (reported line 64)May include surrounding context.

sh
## Prerequisites
- Basic understanding of devtools concepts
- Required tools and access credentials
- System meeting minimum requirements

## Installation

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest claims this skill is a quick lookup/reference tool for GraphQL Client concepts, best practices, and implementation patterns. In practice, the commands print broad, templated devtools text with little to no GraphQL-client-specific content, so the implemented behavior does not substantively deliver the claimed subject-specific reference functionality.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
99% confidence
Finding

The inline reference table claims users can invoke a 'troubleshooting' command for common problems and fixes. However, the dispatch logic only implements 'debugging', so the documentation actively misstates the available interface and can mislead users about how to use the tool.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.