ClawHub
Back to skill

Security audit

代码审查专家

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Python code-review skill with no evident data access, execution, persistence, or hidden security behavior.

Install this if you want a lightweight Python code-review checklist. Be aware that parts of the skill are Chinese-only and the trigger wording may be too broad for non-Python code review requests.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description and invocation scope are broad enough that it may trigger on general requests for feedback, code audits, or submitted code without tighter constraints on language, repository context, or review boundaries. Overly broad routing can cause the wrong skill to activate, leading to unintended file access or application of an unsafe review workflow in contexts the user did not clearly request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and all checklist content are written exclusively in Chinese, which imposes a specific language on users without any indication of opt-in or alternative locale support. Under the policy rules, a skill artifact that forces a language without user choice is a natural-language policy violation unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill hard-codes Python as the review language and role without indicating user choice or fallback behavior. This can create mismatches where non-Python content is reviewed under incorrect assumptions, potentially producing misleading analysis or causing inappropriate handling of user requests.

Content

No source excerpt is available for this finding.