ClawHub
Back to skill

Security audit

SDD Global Change

Security checks for vulnerabilities and agentic risk

Overview

This skill is a manual, confirmation-gated helper for editing scoped SDD global documentation, with a disclosed Chinese-language workflow and no hidden execution or persistence.

Install this only for projects where global SDD documentation is expected to be maintained in Chinese. Review the proposed change plan before confirming, because the skill can make persistent edits to spec/global documents and generate image files under the configured workspace.

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
97% confidence
Finding

The skill hard-codes Chinese-only user-facing output and Chinese-only document content without checking the user's language preference or the repository's established language policy. This can cause unauthorized or harmful content transformations in multilingual or English-language repositories, degrading integrity and usability of documentation even when the requested semantic change is correct.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.