ClawHub
Back to skill

Security audit

Executing Plans

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain workflow guide for executing implementation plans and does not contain hidden code, persistence, credential use, or network behavior.

Install this only if you are comfortable with a Chinese-language workflow skill or can reliably translate it. It is intended to guide code changes from a written plan, so review the plan and make sure the agent pauses for blockers, verification failures, and main/master branch changes as described.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructions are entirely in Chinese with no language selection or opt-in, which can cause the operator to misunderstand critical workflow and safety requirements. In a plan-execution skill, misunderstanding steps like review checkpoints, stop conditions, branch restrictions, or required verification can lead to unsafe or unintended code changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.