ClawHub
Back to skill

Security audit

Merge Pr Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Gitee PR merge assistant that checks PR details and only merges after explicit user confirmation.

Install this only if you intend to let the agent evaluate and merge Gitee pull requests through your configured Gitee MCP access. Before confirming a merge, verify the repository, PR number, target branch, CI status, and review state, because the merge action is irreversible.

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
85% confidence
Finding

The skill advertises broad trigger phrases like "merge PR" and "can this PR be merged," which can match routine conversation and cause the skill to activate in contexts the user did not intend. Because this skill can lead to an irreversible merge action after a lightweight review flow, over-broad invocation increases the chance of accidental high-impact repository operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.