ClawHub
Back to skill

Security audit

头脑风暴

Security checks for vulnerabilities and agentic risk

Overview

This brainstorming skill’s fact-checking searches fit its purpose, with privacy and usage-cost considerations but no material security concern.

Search queries go to external providers, so use generalized wording and exclude personal or confidential details. Set search and spending limits, and keep control over when discussions end.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (1)

Mandatory web searches lack a warning about disclosure of discussion-derived information to external search services.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill mandates web searches and repeatedly reinforces searching discussion-derived facts without requiring a sensitivity check, query sanitization, or user consent before external disclosure. In a brainstorming skill covering workplace, psychological, and business topics, queries could reveal personal information or confidential plans to search providers, although the skill does not explicitly direct disclosure of secrets or identify an attacker-controlled destination.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.