ClawHub
Back to skill

Security audit

Processing Capacity Planner and Job Queue Register

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed workload-operations helper with no bundled code, credentials, private-file access, or hidden persistence.

Before installing, treat this as a workload-operations helper for selecting and recording processing profiles; users who need tighter activation should ask the publisher to make the trigger wording more specific.

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
89% confidence
Finding
The phrase 'Use this skill for routine workload operations work' is broad and does not define specific activation phrases, scope boundaries, or exclusion conditions. In a markdown skill description, this can cause unintended invocation because many ordinary operations requests could appear to match.

Static analysis

No suspicious patterns detected.