ClawHub
Back to skill

Security audit

Code Handover Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation assistant for understanding handed-over codebases and shows no evidence of hidden execution, exfiltration, persistence, or destructive behavior.

Install this when you want a structured handover document for a codebase. Be deliberate about which repository or path you ask it to inspect, especially if the project contains sensitive business logic or secrets, and request English or another language explicitly if Chinese documentation is not desired.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation guidance includes very broad, everyday phrases such as asking to 'look at this project' or 'take over this code', which can cause the skill to activate in contexts where the user did not explicitly request a full handover workflow. That increases the chance of unintended execution, over-collection of repository context, and steering the agent into a larger analysis process than the user intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Mandating Chinese as the default output language without user opt-in can override user expectations and system language preferences, which is a prompt-scope/control issue. In security-sensitive or operational contexts, forced language switching can reduce reviewability, cause misunderstandings, and make it harder for downstream users to validate the generated analysis.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains natural-language instructions that require formal written Chinese and specific Chinese numbering conventions, such as '全程使用正式书面语' and '章节使用中文数字编号'. Because the policy applies universally within the document and does not offer opt-in, alternatives, or a stated region-specific justification, it is a language/locale policy violation under SQP-3.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.