ClawHub
Back to skill

Security audit

architecture-paradigm-microkernel

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only architecture guidance skill with no commands, persistence, credential handling, or hidden behavior.

This skill is safe to install as architecture reference material. Be aware that broad trigger words may cause it to appear in some unrelated design conversations, but it does not request sensitive access or perform actions.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest trigger phrases include generic terms like "architecture", "plugin", and "extensibility", which are common in many unrelated technical discussions. Because the file does not provide tighter scope constraints or negative examples in the trigger section, the skill could be invoked in contexts far broader than intended.

Content

No source excerpt is available for this finding.