ClawHub
Back to skill

Security audit

support-case-intake-desk

Security checks for vulnerabilities and agentic risk

Overview

This skill only formats user-provided support snippets into digests or draft case comments, with no code execution, credential use, private-file access, persistence, or network behavior in the artifact.

Install this as a low-risk support drafting aid. Users should still review generated case comments before using them operationally, especially because the package description mentions posting while the inspected instructions only build a comment object.

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
Confidence
93% confidence
Finding
The skill is advertised for broad 'routine support operations work' and says to 'invoke the stage requested by the user,' which can make activation overly permissive and increase the chance the agent selects this skill for loosely related prompts. Unintended activation can cause support-derived content to be generated or posted in the wrong context, especially because the workflow chains from digest preparation to case-comment construction for operational use.

Static analysis

No suspicious patterns detected.