ClawHub
Back to skill

Security audit

architecture-paradigm-functional-core

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small architecture-guidance document and does not request execution, credentials, persistence, or privileged access.

This appears safe to install as architecture advice. Users should know it may activate for general discussions about architecture, testability, or business logic, so its guidance should be treated as optional design input rather than an automatic refactoring mandate.

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
89% confidence
Finding

The trigger list includes a long natural-language phrase, 'business logic is entangled with I/O or unit tests are slow and brittle,' which is broad enough to match ordinary architecture discussions outside the narrow intended use case. In an agent skill system, overly broad triggers can cause unintended activation, injecting irrelevant architectural guidance into unrelated conversations and reducing reliability of agent behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.