ClawHub
Back to skill

Security audit

account-record-consolidation-desk

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives instructions for deriving and applying account-record merge guidance from user-supplied data, with no hidden code, credentials, persistence, or external access.

Install only if you want agents to help consolidate account-record fields. Users should make explicit stage requests and review generated merged records before applying them to any real business system.

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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The workflow description says to use the skill for 'routine account maintenance work' and then 'invoke the stage requested by the user,' which is broad enough to match generic account-related requests without strong gating. In an agent setting, this can cause unintended tool selection or execution of consolidation actions when the user's intent is ambiguous, increasing the chance of unauthorized or incorrect record changes.

Vague Triggers

Low
Confidence
83% confidence
Finding
The Stage 1 activation text only says to use the skill when the user 'asks to set account merge guidance,' but it does not define concrete trigger phrases, authorization expectations, or disambiguation rules. That weak boundary can let loosely related requests be interpreted as approval to derive merge guidance, which may bootstrap later merge operations from incomplete or attacker-shaped input.

Vague Triggers

Low
Confidence
83% confidence
Finding
The Stage 2 trigger language similarly relies on a generic request to 'merge an account revision' without requiring proof that the merge was intentionally requested within the proper workflow. Because this stage performs the more sensitive action of producing a merged record, ambiguous triggering could lead to unintended consolidation, data corruption, or acceptance of attacker-provided merge guidance.

Static analysis

No suspicious patterns detected.