ClawHub
Back to skill

Security audit

Cognitive Debt Guard

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only code review checklist for AI-generated code, with no executable payload, credential handling, network access, or hidden privilege requests.

Before installing, expect this skill to nudge AI-code and code-review conversations toward comprehension checks and stricter review discipline. Its research statistics are not independently substantiated inside the artifact, so treat them as discussion prompts rather than verified facts.

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 trigger list includes generic conditions such as 'User asks about code review' and 'User mentions "AI code", "generated code", "copilot wrote"' without narrowing context or providing exclusions. In a markdown skill file, this kind of broad natural-language trigger can overlap with ordinary discussion and does not clearly define when the skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.