ClawHub
Back to skill

Security audit

AI KEY·我该卖什么

Security checks for vulnerabilities and agentic risk

Overview

This product-planning skill fits its stated purpose, but retains planning lessons and requires separate AI KEY reference files.

Expect rejected product directions and successful methods/results to be remembered. Check the configured memory location and its retention settings before discussing confidential plans. Required AI KEY family references are not bundled and were not assessed; obtain and review them before use. The skill should stop if its mandatory convention is unavailable.

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)

The skill instructs the agent to persist user-specific business information without warning the user.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill explicitly directs the agent to persist rejected product directions and validated methods with their results in configured memory, without requiring notice or checking whether the user authorized retention. These records can contain confidential business decisions or commercial outcomes and may subsequently surface outside their original context if memory is shared or reused. The legitimate personalization purpose and absence of an external transmission destination reduce concern about malicious intent, but do not address unintended retention.

Content

No source excerpt is available for this finding.