ClawHub
Back to skill

Security audit

Program Derivation

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for architecture and code-quality analysis, with broad activation wording but no hidden execution, persistence, credential access, or destructive behavior.

Install only if you want a general architecture-analysis and metrics skill. Be aware it may be invoked for broad software-quality or refactoring requests, and the referenced supplemental checklist files are not included in the package.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description contains very broad activation terms such as architecture analysis, interface design, complexity measurement, refactoring planning, and software quality assessment, without clear boundaries or exclusions. This can cause the agent to invoke the skill for many generic engineering requests, potentially overriding more appropriate specialized skills and leading to scope creep, confused behavior, or unsafe use in contexts the skill was not designed to handle.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The when-to-load section repeats expansive and ambiguous criteria for common software-engineering activities in both German and English, making activation likely across a wide range of normal requests. In skill-routing systems, such broad criteria increase the chance of inappropriate attachment, which can distort analysis workflows, cause unnecessary file access or reasoning steps, and reduce trust in routing decisions.

Content

No source excerpt is available for this finding.