ClawHub
Back to skill

Security audit

stewardship

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only stewardship guidance skill with no hidden execution, credential access, or persistence, though some triggers are broad enough to invoke it more often than intended.

Install this if you want general stewardship and code-quality prompts during plugin work. Be aware it may activate on broad topics like quality or maintenance, and review any optional external Claude Code plugin separately because this OpenClaw artifact does not include those hooks or commands.

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
Confidence
95% confidence
Finding
The trigger list contains broad, generic terms such as "quality," "culture," and "maintenance" that can match many unrelated user requests. This can cause unintended invocation of the skill, leading to prompt/context pollution and potentially steering the agent into an irrelevant workflow when users did not request stewardship guidance.

Static analysis

No suspicious patterns detected.