ClawHub
Back to skill

Security audit

Doc Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent document-generation orchestrator that creates task-scoped draft, state, and final files as part of its stated purpose.

Before installing, expect the agent to create and update task-specific Markdown and JSON files and to merge generated chapter files. Use it in a dedicated project or task directory if you want to avoid clutter or accidental filename collisions.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs the agent to create and update JSON/Markdown files and shows shell-based merge steps, but it never explicitly warns that these actions will modify the workspace. In an agent setting, silent file creation and shell-assisted writes can surprise users, overwrite existing artifacts, or operate on unintended paths if task variables are mis-scoped, even though the overall orchestration purpose appears legitimate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.