ClawHub
Back to skill

Security audit

Review

Security checks for vulnerabilities and agentic risk

Overview

This is a plain review-guidance skill with no code, persistence, credential use, or hidden actions, though its activation wording is broad.

Install this if you want many kinds of feedback requests to receive a structured critique format. Be aware that casual phrases asking for an opinion may trigger it, so users who prefer narrower activation may want the trigger wording tightened.

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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger description is broad enough to match many routine phrases such as 'what do you think' or 'check this for me,' which can cause the skill to activate in contexts far beyond deliberate review requests. Over-broad activation increases the chance of inappropriate routing, unintended disclosure of user content to the wrong workflow, and interference with more specialized skills that should handle the request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.