ClawHub
Back to skill

Security audit

Dotnet Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a .NET coding guidance skill with broad triggers and some inconsistent sample guidance, but no hidden execution, persistence, or data-access behavior.

Installers should be aware that this skill may trigger for generic C# or .NET terms and its validation pipeline sample should be reviewed before copying into production, but the artifact does not show hidden execution, credential access, exfiltration, or persistence.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad terms such as '.NET', 'controller', 'migration', and 'C#', which can cause the skill to activate in loosely related conversations. In an agent environment, over-broad activation increases prompt-surface exposure and can lead to inappropriate code-generation behavior, security-relevant advice in the wrong context, or untrusted instructions being given more authority than intended.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill repeatedly documents a preference for returning Result errors rather than throwing exceptions, including the explicit guidance at L037 and L238-L249. However, the ValidationBehavior implementation throws a ValidationException when validators fail, which directly contradicts that stated intent for handling validation/business failures.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
95% confidence
Finding

Using 'C#' as a standalone trigger is especially prone to accidental invocation because it is short, generic, and likely to appear in many unrelated requests. While not directly enabling code execution, it increases the chance that this skill is selected outside its intended scope, which can amplify bad guidance or expose downstream systems to unnecessary agent actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.