ClawHub
Back to skill

Security audit

Doc Co

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent document co-authoring workflow with user-directed file edits and optional context gathering, not a hidden or unsafe capability.

Before using it with company documents or team channels, make sure you are comfortable sharing that context with the connected tools or sub-agents used for reader testing. The skill is otherwise a normal guided writing workflow.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The phrase "User seems to be starting a substantial writing task" is broad and subjective, and it does not clearly define when this workflow should or should not be offered. Because this is a markdown skill description, such ambiguity can cause the skill to activate for many ordinary writing-related conversations beyond the intended document co-authoring use case.

Content

No source excerpt is available for this finding.