ClawHub
Back to skill

Security audit

深度话题调研工作流

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent research workflow with an optional user-requested Obsidian note export, but users should confirm the target note path and write behavior before using that option.

Installers should treat this as a research/report-writing workflow. If using the Obsidian option, provide an exact note path and ask the agent to confirm whether it will create, append to, or overwrite the file before it writes.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Low
Confidence
91% confidence
Finding
This markdown file applies to SQP-2, and it explicitly offers '写入Obsidian笔记' as an output mode. The skill description does not include any user warning about file modification risks, path correctness, or possible overwrites, even though writing notes can affect user data.

Missing User Warnings

Low
Confidence
94% confidence
Finding
The skill allows writing to a user-specified Obsidian file path without stating any safeguard against overwriting existing content or creating files in unintended locations. In an agent setting, this can lead to accidental data loss, clobbering notes, or unauthorized modification of user files if the path is ambiguous or manipulated.

Static analysis

No suspicious patterns detected.