ClawHub
Back to skill

Security audit

dispatching-parallel

Security checks for vulnerabilities and agentic risk

Overview

This is a broad, generic parallel-task automation skill with shell/API-related wording, but the artifact does not contain hidden code, persistence, exfiltration, or destructive behavior.

Install only if you want a broad development automation helper for independent parallel tasks. Keep normal approval prompts for shell commands and external API use, and avoid giving it credentials or sensitive files unless the specific task requires them.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation guidance is extremely broad, covering generic efficiency, automation, batch processing, workflow optimization, development automation, and data analysis without meaningful constraints. In an agent ecosystem, this makes unintended or overly frequent invocation likely, which is particularly risky here because the skill advertises command execution and external data/API use, increasing the chance that unsafe actions are triggered in contexts the user did not explicitly intend.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description does not clearly warn users that it may execute commands and interact with external APIs/data sources, despite the tool list including exec and the document referencing API keys, GitHub-sourced data, and integrations. This can mislead users and calling agents about the operational risk boundary, leading to accidental execution, data exfiltration, or unexpected external side effects without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.