ClawHub
Back to skill

Security audit

review-core

Security checks for vulnerabilities and agentic risk

Overview

This skill is a review checklist that structures evidence gathering and reporting, with no hidden code execution or persistence.

Install this if you want a general checklist for structured reviews. Be aware that its broad review and analysis triggers may make it appear in many assessment-style conversations, but the instructions are disclosed and limited to organizing review work.

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 set is broad enough to match ordinary review-related language such as 'review', 'analysis', or 'assessment', which can cause this skill to auto-load in many unrelated contexts. Unintended invocation is risky because it can alter workflow, inject procedural instructions, and create prompt-scope interference with more specific or security-sensitive skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.