ClawHub
Back to skill

Security audit

Triage Issues

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Gitee issue triage helper that can update issues only after user confirmation.

Install this only for repositories where you want an agent to help triage Gitee issues. Before approving updates, review the target repository, selected issue batch, labels, priorities, assignments, and any comments because confirmed actions may change project-visible issue data.

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
96% confidence
Finding

The manifest description lists generic activators such as "show me all open issues" and "categorize issues," which are broad phrases a user might say in many contexts. The description does not provide clear scope limits or negative examples, so the skill could be invoked unintentionally for everyday repository-discussion requests.

Content

No source excerpt is available for this finding.