ClawHub
Back to skill

Security audit

Skill Philosophy Validator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only design reviewer for OpenClaw skill files and does not show hidden execution, persistence, credential access, or data exfiltration behavior.

Install this if you want automatic skill-design validation after SKILL.md edits. Be aware that its trigger scope is broad, so it may run during ordinary skill editing and produce review guidance even when you did not explicitly ask for a separate validation pass.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (3)

Self-Modification

High
Category
Rogue Agent
Confidence
95% confidence
Finding

The skill declares activation on phrases such as 'update skill' and 'modify skill' while itself operating on SKILL.md files, creating a self-modification / self-targeting risk. In agentic environments this can lead to recursive review-edit loops, accidental rewriting of the validator itself, or unsafe prompt chaining where a skill influences its own future behavior without clear user intent.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: skill-philosophy-validator
description: Validates skill design against five core principles. Trigger after a SKILL.md file is created, written, edited, modified, or optimized. Also trigger when user asks to "validate skill", "check skill design", "review skill quality", "optimize skill", "improve skill", "update skill", "refine skill", "优化 skill", "改进 skill", "更新 skill", "修改 skill", "验证 skill", "检查 skill 设计", "审查 skill 质量". Do NOT trigger when the user is merely reading or viewing a SKILL.md without making changes.
metadata: {"openclaw": {"emoji": "🔍"}}
---

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger description is overly broad because it activates on common edit-oriented phrases like 'optimize skill', 'improve skill', and generic SKILL.md modification events. This can cause the validator to run in many routine editing contexts where it was not explicitly requested, increasing the chance of unintended workflow interference, prompt shadowing, or recursive invocation alongside other skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file is written as a normative reference manual in Chinese and does not indicate that language selection is optional or region-specific. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.