ClawHub
Back to skill

Security audit

定位代码逻辑

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow code-navigation skill that reads project files to find relevant implementation locations and does not show hidden execution, persistence, or data exfiltration behavior.

Install only if you want an agent to inspect code in the current workspace to answer implementation-location questions. Provide a concrete problem and entry file, and avoid using it on repositories whose source code should not be summarized back into chat.

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
93% confidence
Finding

The skill description and trigger guidance include very broad everyday phrases such as '代码在哪', '找实现', and '定位逻辑', which can match many normal coding conversations unrelated to this specialized workflow. In an agent environment, overly broad activation can cause the wrong skill to run automatically, leading to mis-routing of user intent, unnecessary repository traversal, and unintended exposure of code context or file contents.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.