ClawHub
Back to skill

Security audit

Repo Explorer

Security checks for vulnerabilities and agentic risk

Overview

This skill gives an agent a structured way to read a specified Gitee repository and summarize it, with no hidden code execution or persistence.

Before installing, make sure you intend to use Gitee-backed repository inspection and only provide repositories whose contents you are comfortable letting the configured Gitee MCP server read and search.

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
91% confidence
Finding

The skill uses broad activation phrases such as "explore a repository," "tell me about this repo," and "what does this repository do," which can match a wide range of ordinary user requests without clear scoping constraints. This increases the chance the skill is invoked when the user did not explicitly intend to use Gitee-backed repository inspection, potentially causing over-broad tool use or unintended data access paths.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.