ClawHub
Back to skill

Security audit

security-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent defensive code security review guide with no executable code, persistence, credential handling, or hidden data movement.

Install this when you want a structured defensive security-review workflow. Expect it to read relevant code in the scope you provide and run search or audit commands when appropriate, but it should report findings and ask before drafting fixes.

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
95% confidence
Finding

The description says to use this skill when the user says phrases like "is this secure" and "threat model this" even if they do not name the skill. These are broad, natural phrases that can arise in ordinary conversation, and the file does not provide negative examples or tighter scope constraints in the trigger list itself.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The "When to use this skill" section mixes direct phrases with broad situational conditions such as code being about to ship or another skill surfacing a concern. Without explicit limits on when these conditions do not apply, the activation scope remains subjective and may overlap with routine code review.

Content

No source excerpt is available for this finding.