ClawHub
Back to skill

Security audit

Superlative Memory Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed automatic memory manager, but users should understand it may retain conversation-derived information for long periods.

Install this only if you want automatic persistent memory. Review retention settings, avoid storing secrets or highly sensitive personal data unless your environment has appropriate controls, and confirm how the underlying memory skills support review and deletion.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly describes persistent, multi-tier memory storage including vector databases, git notes, backups, and archives, but never warns that user inputs and conversation-derived data may be retained across these layers. This creates a real privacy and data-governance risk because users may disclose sensitive information without understanding that it can be stored long-term, replicated, and later recalled.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Saying the skill works automatically with no manual intervention means conversation content may be compacted, transformed, compressed, and moved between storage tiers without explicit user awareness or approval. That is dangerous because automatic summarization and migration can both preserve sensitive content unexpectedly and alter records in ways that affect privacy, accuracy, and downstream recall.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This manifest file describes a wide range of capabilities such as cognitive memory, context compaction, and semantic recall, but it does not indicate when the skill should activate or any limiting conditions. In a manifest-scoped review, that lack of specificity can contribute to unintended invocation because the skill's scope appears generally applicable to many conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.