ClawHub
Back to skill

Security audit

记忆整理 (Memory Curator)

Security checks for vulnerabilities and agentic risk

Overview

This memory-curation skill is transparent and purpose-aligned, but it can delete memory entries and update MEMORY.md, so users should review changes before applying them.

Install only if you want an agent to maintain persistent memory. Ask it to show the memory IDs it plans to delete and any MEMORY.md diff before applying changes.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill includes deletion of memory entries as a normal workflow step but does not require an explicit warning, confirmation, or recovery mechanism before destructive changes. This is dangerous because memory deletions may irreversibly remove important persistent context, including user preferences or project history, especially if the validation step is performed incorrectly or incompletely.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs syncing important structured memory into MEMORY.md, which is a persistent file modification, but it does not require a user-facing warning or confirmation before writing. This is dangerous because it can silently alter long-lived memory artifacts, causing accidental disclosure, corruption, or persistence of incorrect summaries without the user's informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language instructions and examples are entirely in Chinese, and the skill does not indicate that users may interact in another language or that Chinese is a required, justified locale. This can amount to a language-policy issue when a skill implicitly forces one language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.