OpenClaw Shield Quick Scan

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 6:50 PM UTC
• Version: 1.0.0

Overview

This skill is a straightforward wrapper for running a user-directed OpenClaw Shield scan and summarizing its JSON report, with no hidden persistence or exfiltration behavior found.

Install only if you intend to run local security scans. Point target_path at the specific folder or repository you want scanned, use a trusted OpenClaw Shield scanner path, and review the generated report before acting on findings.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The implementation is a report summarizer, not a scanner. It accepts a path to a JSON report, parses findings from various keys, normalizes severity labels, counts findings, and prints the top N entries. There is no code to traverse a folder, inspect a repository, invoke OpenClaw Shield, or analyze files for the security behaviors named in the description. While summarization matches part of the description, the primary declared capability—running a fast scan for quick triage—is absent, making this a material description-to-behavior mismatch.

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill instructs the agent to read paths and invoke local scripts, but it declares no explicit tool scope or permissions boundaries. In an agent environment, missing scope metadata can allow broader-than-intended file access or command capability, increasing the chance of misuse against sensitive local paths.