ClawHub
Back to skill

Security audit

Agent Sequential Thinking

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent sequential-thinking guide, but it asks agents to persist detailed thinking records without clear user consent, retention, or redaction rules.

Review this skill before installing if your tasks may include private data, credentials, business plans, or other sensitive context. Use it only with clear rules for when it activates and whether any thinking records may be saved, and avoid persisting raw reasoning or secrets unless the user explicitly opts in.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The auto-trigger conditions are overly broad and ambiguous, such as activating on tasks with multiple steps, complexity above an unspecified threshold, or when the user merely says to 'think a bit'. In an agent skill, this can cause pervasive invocation of hidden reasoning workflows, increasing the chance of unnecessary data collection, persistence, or use of downstream tools without clear user intent or consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs recording detailed thinking traces to a local file under memory/thinking-YYYY-MM-DD.md without any warning, consent flow, retention policy, or guidance on handling secrets. Because internal reasoning may include user data, credentials, strategy, or other sensitive context, writing it to disk creates a persistent disclosure surface that could be exposed to other tools, users, backups, or later prompts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

整份技能说明与示例均以中文呈现，且未说明这是可选语言偏好，也未提供多语言或用户选择机制。按照语言/地区政策，这可能构成未获用户同意的语言限定。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest description is written entirely in Chinese, which imposes a specific language/locale in user-facing skill metadata without indicating that other languages are supported. The policy allows locale constraints only when they are explicitly justified or when the user is offered a choice, neither of which is present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.