ClawHub
Back to skill

Security audit

学习日志系统

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workspace learning journal that persistently writes notes, but I found no hidden networking, credential use, destructive behavior, or deception.

Install this only if you want the agent to keep durable learning notes in your workspace. Avoid letting it record secrets, credentials, private customer data, or sensitive incident details in MEMORY.md or .learnings files.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill clearly instructs the agent to read from and write to workspace files such as MEMORY.md and dated journal files, but it does not declare any tool scope or allowed-tools constraints. This creates an authorization gap where a broadly triggered skill can perform filesystem actions without explicit, reviewable limits, increasing the chance of unintended writes, overwriting sensitive files, or storing sensitive task data in inappropriate locations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger conditions are very broad, covering common events like task completion, failures, discoveries, and important decisions, which are routine in many sessions. In combination with file-write behavior, this can cause the skill to activate excessively and persist large amounts of context, including sensitive prompts, errors, decisions, or workspace-specific information, without clear user intent each time.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains all headings, instructions, and examples in Chinese, and nowhere indicates that the user can choose another language or that the content is intentionally restricted to a Chinese-language audience. Under the policy rule for natural-language violations, forcing a specific language without opt-in is in scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The module docstring presents the tool name and usage entirely in Chinese, and user-facing output elsewhere in the file is also Chinese-only. This imposes a specific language choice without offering the user any locale or language option, which matches the language-policy violation criterion.

Content

No source excerpt is available for this finding.