Back to skill

Security audit

得到大脑(原 Get 笔记)

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because its connection setup is reported to synchronize other Skills despite promises against those changes; the evidence is incomplete.

Review the reported Skill synchronization and decide whether you want those persistent changes before installing. The scan was partial: three local references could not be resolved, so the evidence does not cover everything.

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
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

First-connection setup synchronizes other Skills despite an explicit promise not to modify other Skill files.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

The first-connection workflow requires getnote setup, explicitly described as synchronizing five domain Skills, despite promising not to modify other Skill files. This expands a connection request into persistent changes to agent instructions without separate authorization; using the official CLI limits suspicion of malicious intent but does not resolve the scope violation.

Content

No source excerpt is available for this finding.

The connection workflow installs or updates domain Skills despite the manifest's promise not to install or update Skills autonomously.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The connection procedure automatically runs getnote setup, which this reference documents as installing or synchronizing local agent Skills. A user requesting login or connection has not necessarily authorized persistent instruction changes, and protecting only the independent aggregate Skill leaves the five domain Skills outside that protection.

Content

No source excerpt is available for this finding.