ClawHub
Back to skill

Security audit

Review Lens

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only code review aid with broad but purpose-aligned activation guidance and no executable, network, persistence, or hidden behavior found.

Install this as a code review helper if you want broader correctness-focused review prompts. As with any review skill, use it on repositories or diffs you intend the agent to inspect, especially when the code involves money, auth, or user data.

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
90% confidence
Finding

The 'When to Invoke' section uses broad conditions such as 'Before every PR' and 'When you have a nagging feeling something is wrong' without defining explicit trigger phrases, scope limits, or exclusion conditions. In a markdown skill description, this can lead to ambiguous activation boundaries and unintended invocation in routine development conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.