ClawHub
Back to skill

Security audit

OpenClaw ADR

Security checks for vulnerabilities and agentic risk

Overview

This ADR skill is a straightforward local document helper that creates, reads, and updates Architecture Decision Record files in a project ADR directory.

Before installing, users should expect this skill to create and modify ADR markdown files in their project under docs/adr. It does not show network access, credential handling, hidden persistence, or destructive behavior, but clearer permission metadata would make the intended filesystem scope easier to audit.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill advertises file-reading and file-writing behavior through its documented commands and generated outputs, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization ambiguity: an agent or reviewer cannot easily determine the intended file access boundaries, increasing the risk of overbroad filesystem access or misuse when the skill is invoked in a larger automation environment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains core user-facing instructions and feature descriptions in Chinese while other sections are in English. Under the policy, forcing or assuming a language/locale without opt-in can be a natural-language policy violation when no choice or justification is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.