ClawHub
Back to skill

Security audit

Config Review Flow

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a cautious configuration-review workflow with explicit user confirmations before any real changes are applied.

Before installing, understand that the skill is meant to slow configuration work down into an explicit review process and will write a local tracking Markdown file. Keep the review scope narrow and verify the final summary before approving any real configuration change.

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)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description mixes English with Chinese invocation examples (逐条核对配置, 逐项确认配置) as activation language, but the file does not state that the skill is region-specific or that users may invoke it in any language. Under the policy, language or locale constraints should be optional or clearly justified rather than implicitly embedded.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.