Back to skill

Security audit

Encrypt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small reference/documentation tool that prints static guidance and does not access credentials, networks, or user data.

Installation appears low risk from the inspected artifacts. Users should treat it as generic reference material, and be aware that one cheatsheet entry names a non-implemented 'troubleshooting' command.

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 (2)

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 security concepts
- Required tools and access credentials
- System meeting minimum requirements

## Installation

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The cheatsheet says the command troubleshooting is an essential command, but the dispatcher only implements debugging and has no troubleshooting case. This is an active mismatch between the skill's inline documentation and its actual behavior.

Content

No source excerpt is available for this finding.