ClawHub
Back to skill

Security audit

Conflict Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is for repository conflict management, but it asks for write access and describes merge and push operations without clear safeguards or user confirmation.

Review this before installing in any repository with important branches. It should require explicit user approval before non-dry-run resolution, restrict which repositories and branches it can modify, avoid accepting arbitrary command lists unless tightly controlled, and define authentication and audit behavior for the HTTP endpoints.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill exposes a write-capable conflict resolution endpoint that can perform merges and potentially push repository changes, but the documentation does not clearly warn users that the operation is destructive or state-changing. In this context, callers may assume the API is informational like the scan endpoint, increasing the risk of unintended merges, branch modification, or repository state corruption through misuse or over-trusting AI-suggested resolutions.

Content

No source excerpt is available for this finding.